text
stringlengths 44
950k
| meta
dict |
|---|---|
N.K. Jemisin’s master class in world building (2018) [video] - rrampage
https://www.youtube.com/watch?v=I6xyFQhbsjQ
======
Dahoon
A video with only audio? This is like those pictures of text on Reddit and
Twitter. Ugh.
| {
"pile_set_name": "HackerNews"
} |
An overview of OCaml - amirmc
http://simongrondin.name/?p=330
======
DonPellegrino
Author here, I originally posted this to
[https://www.reddit.com/r/ocaml](https://www.reddit.com/r/ocaml) to gather
some feedback prior to posting it here. It was a surprised when my boss told
me "Hey, you're top 10 on HN right now". Glad to know someone liked it enough
to post it here before I could :)
It's something I've been working on for quite a while, because I wanted to
answer the question "Why do you like OCaml so much and why should I care?"
once and for all. Hope you enjoy it.
Speaking of OCaml, all the traffic going to my blog is going through HARchiver
[0], a very high performance proxy and reverse-proxy 100% written in OCaml
that gathers datapoints for use with Mashape Analytics [1]. Disclaimer, I work
at Mashape.
[0]
[https://github.com/Mashape/HARchiver](https://github.com/Mashape/HARchiver)
[1] [https://www.apianalytics.com/](https://www.apianalytics.com/)
~~~
amirmc
I also added a feed of your OCaml posts to OCaml Planet [1, 2] (just so that
doesn't catch you by surprise) :)
[1] [http://ocaml.org/community/planet/](http://ocaml.org/community/planet/)
[2]
[https://github.com/ocaml/ocaml.org/commit/8df5da9b6fe1ba4c43...](https://github.com/ocaml/ocaml.org/commit/8df5da9b6fe1ba4c4314a81b93db2719cc5ad596)
~~~
DonPellegrino
Thanks, I'm honored!
------
AceJohnny2
Speaking of OCaml, I'm currently working through the Real World OCaml book [1]
by Yaron Minsky, Anil Madhavapeddy and Jason Hickey, who are some of the
drivers of using OCaml in production settings (Yaron Minsky works for Jane
Street, who aside from being a quant firm are also the developers of the
popular Core alternative standard library).
I highly recommend it.
[1] [https://realworldocaml.org/](https://realworldocaml.org/)
------
mrdrozdov
I am not sure where this belongs in the tutorial to intermediate spectrum, but
it feels relevant.
[http://learnxinyminutes.com/docs/ocaml/](http://learnxinyminutes.com/docs/ocaml/)
------
wtetzner
I had trouble accessing the site, so here's a cached version:
[https://webcache.googleusercontent.com/search?q=cache:hHpdNA...](https://webcache.googleusercontent.com/search?q=cache:hHpdNA5YjjQJ:simongrondin.name/%3Fp%3D330+&cd=1&hl=en&ct=clnk&gl=us)
~~~
gkya
I also did, and I also wasn't able to access gnuplot.info, maybe there is a
problem w/ .name?
~~~
edwintorok
gnuplot.info works for me on IPv6 but not on IPv4 (get connection reset on
IPv4), seems to be a problem with projects.sourceforge.net.
gnuplot.info has address 216.34.181.96
gnuplot.info has IPv6 address 2001:468:c80:a202:0:b074:0:c082
96.181.34.216.in-addr.arpa. 3567 IN PTR projects.sourceforge.net.
This site has a different IP and seems to point to a DNS server/proxy:
simongrondin.name has address 176.58.120.112
112.120.58.176.in-addr.arpa. 85642 IN PTR unblock.us.org.
Edit: .name site works now
------
rusabd
> radical at fist first?
| {
"pile_set_name": "HackerNews"
} |
FreeBSD has a new default installer - younata
http://lists.freebsd.org/pipermail/freebsd-arch/2011-March/011170.html
======
munkydung
I hope this means zfs on root is around the corner!
~~~
cperciva
ZFS root has been possible for a long time, providing that you're willing to
set up the filesystems manually.
~~~
X-Istence
ZFS on root using the guides on the FreeBSD wiki is deceptively easy to set
up, and functions extremely well!
| {
"pile_set_name": "HackerNews"
} |
Show HN: BankLocal – Find local banks and invest in growing your community - zapnap
http://banklocal.info
======
bobmarino
Hi,
putting aside the debate over free market theory for the moment, as regards
the banking industry the evidence is very clear and compelling: smaller sized
banks and credit unions do in fact lend a greater portion of their assets to
small businesses. This mainly has to do with the business structure of large
vs. small banking institutions. To quote the FDIC's 2012 Community Banking
Study:
"Community banks tend to be relationship lenders, characterized by local
ownership, local control, and local decision making. By carrying out the
traditional banking functions of lending and deposit gathering on a local
scale, community banks foster economic growth and help to ensure that the
financial resources of the local community are put to work on its behalf.
Community banks have always been inextricably connected to entrepreneurship.
As of 2011, they held 14 percent of banking industry assets, but 46 percent of
the industry’s small loans to farms and businesses."
Analysis of our own data is even more telling: BankLocal data as of 12/31/13
shows that the nation’s four largest banks, JP Morgan Chase, Bank of America,
Citibank and Wells Fargo (collectively known as the Big-Four) only loaned 1.9%
of their combined assets to small businesses compared to 10.6% for small and
medium size banks.
If small businesses and the Main St. economy matter to you, then so should
Local Banking.
~~~
swatow
> _putting aside the debate over free market theory for the moment..._
But this is the central point, whether a person is interested in investing
locally, or investing in small businesses. I already addressed the issue of
investing locally in my top level comment.
> _If small businesses and the Main St. economy matter to you, then so should
> Local Banking._
Free market theory says that there is no reason to prefer small vs large
businesses. Which ever is most efficient will win in the market place, and
will produce the most total welfare. And if income distribution is a concern,
taxation and redistribution is a better way to address this than funding small
businesses.
The term _Main St. economy_ is misleading, because both small and large
businesses contribute to the economy in exactly the same way. There is no way
in which big businesses don't affect or benefit ordinary people.
~~~
mgkimsal
"Which ever is most efficient"
If I care about the most efficient way to make sure money stays local to my
region, dealing with institutions that have a habit of keeping money in a
particular region seems the best way to ensure that happens.
~~~
righttoremember
Efficient is a technical term from economics. It refers to whatever maximizes
total welfare. Total welfare is also a technical term, and is roughly
approximated by GDP.
You don't have to believe efficiency is an important goal (although my post
was arguing that it is). But please let us have this word. Arguments should be
had on the basis of refuting peoples ideas, not depriving them of the use of
any word with a positive connotation.
------
swatow
While I guess it's good to provide people with information that they want, I
disagree with the premise that _Local banks and credit unions work within
established localities and reinvest depositors ' money into local businesses,
farms, and individuals. To put it simply, they often use your money more
responsibly than large megabanks, and your community benefits._
Every business is located somewhere. Why would it be better for a person to
invest in projects located near themselves, than far away? From the way they
phrase it, you'd think that megabanks [sic] throw the money into a black hole,
or otherwise use it in some manner other than investing in businesses (which
again, must be located somewhere).
The movement to buy/invest locally goes against all of economic theory.
Artificial barriers to trade (such as a choice to buy locally) reduce total
welfare, and can rarely be justified in terms of income distribution (because
the best tradeoff between total welfare and income distribution comes from
taxation and redistribution).
~~~
ryanhuff
If the product costs/benefits are equal, why not buy local? Was there an
assumption that buying local is a less attractive deal?
~~~
swatow
If the product costs/benefits are equal, why not buy non-local? It seems like
your avoiding discussing the actual reason I gave for why local vs non-local
is not a valid criterion for judging potential investment opportunities.
In general, if you think that some property of a product is good, then you are
implying that you should buy it even when it would otherwise be a less
attractive deal. In the language of economics, you would say that property
enters your utility/decision function.
------
zapnap
Hi, one of the developers here. This is just a little side project I built
with a financial analyst friend. Uses government data from the FDIC / FFIEC /
NCUA and an open algorithm Bob developed to rank banks based on local impact.
Clearly more we could do here but wanted to release an easy to use tool that
could help people find and promote community banks. Response has been good so
far, just won a social innovation challenge grant. Your feedback and thoughts
(improvements, issues, etc) all very welcome. tia.
~~~
_neil
Seems like a cool idea. Nothing comes up when I search cities in VA. And when
I went directly to their pages I got a rails error:
[http://banklocal.info/locations/va/3174-virginia-beach-
va](http://banklocal.info/locations/va/3174-virginia-beach-va)
[http://banklocal.info/locations/va/827-richmond-
va](http://banklocal.info/locations/va/827-richmond-va)
~~~
zapnap
Ha! My Redis instance just fell over :) Things should be back to normal now.
Apologies for the inconvenience.
Seems like if you just search for 'Virginia' Google Places will plop you down
in a rural part of the states where there aren't any banks within the default
5 mile radius. If you expand that search area a bit (or select a city) you'll
see more options.
Thanks for taking a look!
| {
"pile_set_name": "HackerNews"
} |
Android is now the world’s largest earthquake detection network - AndrewDucker
https://arstechnica.com/gadgets/2020/08/android-is-now-the-worlds-largest-earthquake-detection-network/
======
teleforce
This is a very interesting research prospect and perhaps can be tested in
earthquake prone areas, for example Indonesia regions near the fault lines.
Using the Android smartphone existing sensors (e.g. accelerometer), probably
it can easily detect earthquake once it has happened. Japan has similar
existing alarm system where they send SMS alerts to the residents of affected
cities once any earth quake incident is detected, but not really sure where
and how they put the sensors.
The more interesting approach is a system for prior alert of earthquakes. It
is for predicting soon to happen earthquake, moments (or better several
minutes or hours) before the incident. This is probably feasible due to many
reports that mentioned animals got alarmed and look for cover themselves
moments before the earthquake events[1].
For this prior alert detection maybe a more accurate front-end sensors are
required for example, ADI's AD7768 sensor and connected them to a powerful
cloud based earthquake detection back-end engine [2].
[1][https://www.discovermagazine.com/planet-earth/animals-
sense-...](https://www.discovermagazine.com/planet-earth/animals-sense-
earthquakes-before-they-happen-can-they-help-us-predict)
[2][https://www.analog.com/en/analog-
dialogue/articles/understan...](https://www.analog.com/en/analog-
dialogue/articles/understanding-the-fundamentals-of-earthquake-signal-sensing-
networks.html)
------
Akronymus
I just hope it doesn't use the earthquake detection as justification to make
us unable to disable location data.
Other than that, it is a good example of how crowd sourcing data can be useful
and even life saving.
| {
"pile_set_name": "HackerNews"
} |
Ask HN: Easiest cloud solution to deploy a Tomcat/Mysql/Java app - serverdude
Folks
Although I have worked on amazon ec2 before, it was with an already set up account. I am trying to find the quickest way to deploy a prototype by this weekend. I do not want to use Google App Engine since I would like to use MySQL. I am looking at EC2 and was wondering if someone can tell me what option I should go for. I was considering a shared public AMI (such as http://developer.amazonwebservices.com/connect/entry.jspa?externalID=1725).
I am quite comfortable with doing this on my laptop and I think it should be fairly easy to do so but wanted to see if someone tells me something here at HN that I may not think of.<p>Thank you!
EDIT: I have a very small data (since it is just a prototype) so scalability, performance etc are not important.
======
mickeyben
Why not use a Linode or Slicehost slice.
Of course you'll need to setup the slice by yourself but you shouldn't need
more than few hours and AFAIK it's cheaper (I use Linode and I'm very happy
with it).
~~~
serverdude
Thanx! Is the "set up" as simple as installing stuff (tomcat/mysql/jdk) or is
it more complicated? If so it should be not more than 30 minutes to an hour
max?
~~~
serverdude
Just emailed the linode folks and got a response back! Most likely I would go
with linode. @mickeyben, let me know if i should give your referral or
something (assuming i go with them should decide by tomorrow)...
~~~
mickeyben
Hey serverdude, hope you'll enjoy it as much as I do.
Thanks for the propositions but it's ok.
| {
"pile_set_name": "HackerNews"
} |
The Chinese Internet: Why the “Copy Cats” Win - vaksel
http://www.techcrunch.com/2009/10/28/the-chinese-internet-why-the-%e2%80%9ccopy-cats%e2%80%9d-win/
======
coconutrandom
That was a really good article
Put another way: Sure the Chinese can learn a
thing or two about original Web ideas from the
Valley, but the Web 2.0 generation can learn a
lot about monetization from China.
and it goes to explain with an example with a Chinese version of match.com
~~~
chrischen
I think Chinese people will just relate better to homegrown stuff.
Good thing I'm Chinese. Hopefully I will have a cultural advantage if I decide
to operate there one day.
~~~
bootload
_"... I think Chinese people will just relate better to homegrown stuff ..."_
There are possible explanations to this idea in an article I read yesterday ~
"Welcome to China's millennium", Martin Jacques ~
[http://www.guardian.co.uk/commentisfree/2009/jun/23/china-
ma...](http://www.guardian.co.uk/commentisfree/2009/jun/23/china-martin-
jacques-economics)
------
joblessjunkie
"men are universally attracted to women with a .7 hip-to-waist ratio"?
I suspect that this ratio has been reported backwards.
~~~
swernli
The number is correct, the wording is backwards. Studies have shown that
waist-to-hip ratios (WHR) for women considered attractive within their
cultures hover around average of 0.7. Interestingly enough, variation in
attractive frontal WHR across cultures dissapears when using circumference as
a measurement; in that case it collapsed down pretty reliably to 0.7.
<http://en.wikipedia.org/wiki/Waist-hip_ratio>
~~~
RevRal
I clicked your link, and I have to say that their idea of a really attractive
WHR is really spot on (the example at the top).
The last section is also very interesting. I'd like to see a study done on the
people who find smaller hips more attractive, whether this correlates to less
intelligence.
~~~
jpwagner
_"...whether this correlates to less intelligence."_
I laughed out loud when I read that line. Maybe it is correlated with poor
eye-sight!
~~~
yummyfajitas
It's probably correlated with working in fashion.
<http://boingboing.net/2009/10/06/the-criticism-that-r.html>
------
bnomis
The main reasons local versions are more popular are a combination of:
\- it's in Chinese
\- it's not blocked by the GFW
\- it's faster (the GFW slows access to everything outside of it down)
\- it's still accessible when China Telecom has been tweaking the routers and
DNS servers (which they seem to do every week)
That is, practical reasons which lead to adoption and growth.
There are, of course, cultural specifics that have to be taken into account
but those are pretty obvious if you're building a site in China for the the
local market. And these local touches can only add to the site attractiveness
together with being inside of the GFW. So, it's kind of obvious that a local
site is going to do better than a foreign one.
Occassionally people will talk about designing the look of the site for the
local market but I'm not convinced it's an issue. Good taste is good taste
everywhere. For example, the iPod is just as popular here as everywhere else.
A well designed and functional site in China is always going to win over the
equivalent site that is outside of the GFW for the reasons above.
~~~
est
> the GFW slows access to everything outside of it down
Just FYI: the GFW works in parallel, all backbone cross nation data are copied
to GFW equipments, and GFW actively injects RST packets into backbone
transmissions. I don't see how this slows the Internet down. It's just the
total bandwidth is too small. There has to be more cross-pacific fiber optics.
~~~
bnomis
Yes the GFW is regional - i.e. there's more than one filter across the
country. But the GFW actively monitors and blocks on _content_. This filtering
and inspection takes finite time and hence slows everything down.
There is plenty of bandwidth. Accessing the same sites from Hong Kong is
orders of magnitude faster. And BTW less prone to random errors introduced by
clueless monopoly operators.
~~~
est
> blocks on content
Perhaps you didn't understand how GFW works. The content is delivered to you
after the RST signal, it's just the standard TCP stack ignored it. You browser
may loading a page in half then suddenly Page-Not-Found, but if you have
sniffer like tcpdump you can see the rest of the packets were still sent to
you correctly.
Another phenomenon to help you understand the mechanism is that GFW fails from
time to time. Why? Because the RST packets arrives too late.
HK has its own Internet infrastructure, it has nothing to do with mainland
Internet. In fact lots of inner-China Internet connections are routed to HK
then to the rest of the world.
~~~
bnomis
The fact that RST is sent mid stream in no way lessens the point that the
content monitoring leads to a narrowing of bandwidth which slows things down.
HK's Internet Infrastructure maybe its own but it is still this side of the
Pacific and it is a lot faster to access US sites from HK than it is from
China. And if, as you said, China traffic is routed through HK then the only
difference is the GFW which is slowing things down.
~~~
est
So what's your point? I don't see how GFW slows the Internet down in any way.
Except RST packets bandwidth which is too tiny.
~~~
bnomis
Just because you don't see how it slows things down does not mean that it does
not slow things down. The web in China is slower than the web in HK. Why? I
don't know precisely because I don't have access to the GFW of course. Think
of it as a funnel, the communication has to pass through the funnel so that
the RST (or whatever) can be inserted. There's only so much BW in to and out
of the funnel - so the traffic slows. The very fact the filtering happens must
insert some delay.
Have you tried the web in China?
~~~
est
I am sorry but I don't see any reasonable facts or explanation of how GFW
slows the Internet down. HK is fast because your ISP is fast, it has nothing
to do with GFW. I can download from ThePirateBay with the speed of 37MB/s in
Chinese CERNET, and I can watch Youtube HD/HQ videos in ChinaTeleCom's 1Mb
ADSL smoothly in midnight when the Internet is not busy.
I am a native Chinese living in China. And the tool I am using to visit
youtube does not require any 3rd-party servers, it hacks into GFW and
establish connections to blocked sites directly. :)
------
Dilpil
Wow, that matchmaking service sounds pretty intense. They literally ask women
out for you.
~~~
w1ntermute
And it clearly works; otherwise, there wouldn't be so many women using the
site.
------
dstorrs
The thing that impressed me the most was the discussion of the quantitative
work they have done. Song Li has generated an enormous database of pragmatic,
mathematically proven advice about how to be successful with the opposite
gender...somehow, using it for nothing more than a matchmaking service
restricted to China seems small potatoes. Granted, it was gathered from a
Chinese-only audience, so some of it is probably locale-specific. I'd be
interested to see the same thing done on a more global scale and then adapted
for other uses.
~~~
roundsquare
Yeah. It'd be awesome if they published it the way okcupid was.
------
amix
I think author misses that the Chinese market isn't free and most of the
western sites are blocked by the great Firewall. I think their market would
look at lot differently if their market was free and anyone could compete on
it.
~~~
FooBarWidget
Match.com isn't blocked.
And if I'm a Chinese (I am) in China visiting a western website the first
thing I'd think is "OMG it's not in Chinese", after which I'd go look for a
native version. Some sites do localization, but it's rarely done correctly.
For example search results are still polluted with foreign information and
some pages are only available in English.
~~~
Frazzydee
Not saying that your points aren't valid, but you should know that I've found
western sites generally load far slower than Chinese ones in China. I
completely gave up trying to use facebook without turning off images.
------
ahlatimer
Am I the only one that's getting 403'd when I try to access this page?
~~~
Sam_Odio
It looks like every article on techcrunch.com is down. Probably some apache
rewrite issue.
------
est
I don't think the 'copycats' win, it's just the originals didn't do their
best.
ChinaHR sucks balls
<http://www.google.com/search?q=chinahr+%E7%83%82>
any first year college students can write better .asp pages than that, it's
just many hiring companies are using ChinaHR exclusively and you have to apply
on it.
Digu.com & Zhenai.com has a terrible reputation for spamming and selling
private user data.
The real secret for winning in Chinese market? Marketing and PR. Especially
good relationship with the right Communist party leader.
| {
"pile_set_name": "HackerNews"
} |
Show HN: Data-driven web service for filmmakers only - allenwlee
http://beta.filmquotra.com/register<p>Would love your feedback for our open beta of filmquotra: an online software which acts as your personal studio business analyst while helping you create your custom business plan for your film project.<p>filmquotra provides you immediate, real value based on actual, proprietary film financial data.<p>If you are a film student or first-time filmmaker, filmquotra provides step-by-step guidance on creating a film financing "business model." Even a seasoned professional can run quick film comparables and film ultimates. And for the select industry expert, we provide a way to
monetize industry knowledge in a controlled, organized way. It is free to use during our beta phase.
======
goldfeld
I was initially led to think I wouldn't be allowed in, being only an
enthusiast and reading "filmmakers only". Loved the design and guiding
interface, can't wait for features like the outline and more parts of the
workflow.
Edit: The 'Learn More' link has no href?
~~~
allenwlee
thanks for looking and commenting! good point on the "filmmakers only." The
Learn More link should take you to the help page. /help.html
| {
"pile_set_name": "HackerNews"
} |
Microsoft COFEE leaks all over the Internet - gursikh
http://www.crunchgear.com/2009/11/06/siren-gif-microsoft-cofee-law-enforcement-tool-leaks-all-over-the-internet/
======
anigbrowl
I don't understand why this isn't a hot topic on HN right now. COFEE basically
just installs a suite of mostly standard system administration/analysis tools
onto a USB drive, and can then be used to glean info from a suspect's computer
without disturbing any running processes (so you can see if they've been
logging onto super-illegal-porn.com or dangerously-insecure-server.com etc.).
Plus passwords and other good stuff.
| {
"pile_set_name": "HackerNews"
} |
Ask HN: How do you find work? - Zarathu
I'm a freelance RoR and PHP developer with every other relevant skill set (XHTML, CSS, AJAX, SQL, et cetera), but I'm having a rather difficult time finding work.<p>I'm rushing Craigslist, writing on my blog, and asking everyone I know if they know anyone in need.<p>The economy has been treating me miserably lately, and I haven't had work in over a month. Do any of you guys have tips for me?
======
palish
I found my first job by going to my highschool job fair and begging a guy from
Boeing to let me work as a programmer. He told me I was too young (just turned
17 at the time) but since I was "highly motivated" he would call some friends
on my behalf. He referred me to a local business that develops frimware. After
I explained that I had been developing game development skills for years using
C++, they said I'd probably be a better fit at Ageia (a St Louis company that
developed physics middleware called PhysX, and was recently acquired by
nVidia).
I thought, "How am I going to get the attention of the executives? I'm 17,
there's no way I can just submit a resume and get hired." So I scoured the
internet for any Ageia phone numbers I could find. I called one of them, and a
guy who spoke Chinese picked up. "Um... hello?" and he hung up. But I noticed
a pattern in all of the numbers I found. They all started with the same 5
digits (for example, 555-1212, 555-1286, etc). So I changed the last two
digits to 01 and tried, and nobody picked up. Then I tried 02 and got one of
the top execs on the phone. I convinced him to let me show him some of my
gamedev demos the following day. After that, he told me that he was impressed,
but to prove my skills, I had two weeks to create a demo using PhysX. Two
weeks later, I had created three simple but effective demos.
He seemed pretty impressed at that point, and even told me "you definitely
have a job here". Then I didn't. He couldn't get special permission to hire a
17-year old, because I couldn't sign the NDA. But he asked John Ratcliff (who
worked at Ageia at the time) if he knew of any local companies I'd be a good
fit at. He did, and it turned out that there was a gamedev studio about 30
minutes away from where I lived. I was really excited, and they invited me to
take their programmer test.
The guy who handed me the test said "I hope you know your C++"... he wasn't
exactly confident in me, apparently. (I don't blame him, most candidates
suck.) But I took the test and got a decent score. Up next was the interview
phase, where around 8 programmers came in and sat at a large table in the
conference room. I presented my demos to them (including my three previous
Ageia demos).
I dropped out of high school and worked there as an unpaid intern for about 8
months, at which point I was hired and worked there for three years. Also, the
time between the job fair and my first day on the job was several months, so
the whole process took a lot of effort.
So my advice is, demos are key; talk to the decision-makers, not the
middlemen; and demonstrate your skill in every other possible way (but mostly
shut up and let other people talk, because you don't know 1/10th of what you
think you know).
Also, be genuinely interested in other people. Almost everyone likes the idea
of being a mentor.
~~~
mistermann
"So my advice is, demos are key"
Exactly correct. If you don't have any, you're likely not as skilled as you
think.
~~~
oemta
Ok, so demos are great to have. As a person in charge of hiring, what kind of
demos would you like to see in a candidate? What kind of portfolio should a
person without demos try to develop for the purpose of trying to get a job?
~~~
sanswork
It depends on the job. I'm hiring web devs at the moment so cool functioning
sites are great(but rare). I'm certain a few little games I wrote in
javascript(blackjack, and copies of a few of the games from kde games) got me
my first job in web development. The CTO loved the blackjack game in
particular.
I guess the best advice would just be anything interesting that shows off your
skills.
------
jacquesm
Hm. My work finds me most of the time, but every now and then I'm running on
'idle' for a month or more and I start to look around. One of the things I've
found over the years that it pays big time to keep in contact with all your
business buddies. Let them know you exist and that you still remember them and
every now and then a job will pop out of that.
Networking is a thing that I seriously hate, you won't find me on cocktail
parties / friday get togethers, I live far away from my customer base but an
occasional email does wonders in staying attached and maintaining mindshare.
It's a bit like a pipeline, jobs are always pushed in on one end and out the
other when they're done, if you neglect the 'in' queue while focusing on a job
you'll see a longer gap by the time that you're ready for the next one. That's
a tricky balancing act when you are a single freelancer, maybe teaming up with
a few other people with similar or complimentary skills would help you to find
work easier, and if too many people say 'yes' at the same time you can always
divide the load.
Also, the economy really is down, and lots of tech projects are on hold or
being scrapped right now, this is not the best time to be looking for work.
~~~
Zarathu
Thanks for this. I need to network a little more.
~~~
byrneseyeview
Be careful about what you do when you 'network'. If you contact people without
a having a good reason for it, they'll learn to think of you as someone who
doesn't value their time. Instead, it's just good to get in the habit of
thinking, every time you learn something, "I wonder who among my business
contacts would find this most useful."
~~~
jacquesm
Yes, that's an excellent point, I make sure I really do have a reason. Part of
that is to keep an eye out for stuff that is useful to my 'network' and
alerting people to that. The funny thing is that they repay in kind and you'd
be amazed at some of the stuff that comes 'back' to me in this way. It really
does seem to work like the karma counter on this site.
------
amjith
Write tutorials on your blog. Don't hesitate to share your knowledge. Even if
you don't have great writing skills, people are attracted to quality content
and tips & tricks. Put a link on your blog that you are available for hire.
Publicize your blog through the right medium (reddit, digg, dzone).
There are plenty of wall in the hole restaurants that don't have a good
website. Offer to build them one for just $100, it doesn't take more than 3
hours to finish a website for a small restaurant. Some of the mom and pop
restaurants don't even know how to host websites, so offer them to do all the
hosting and maintaining for them in exchange for free food every week (or an
extra fee of say $100). Put a webcounter and keep track of who is visiting and
try to publicize it in Yelp, local.Yahoo, local.Google etc. Expand your offer
to small businesses (clothing stores or boutiques) and show them your
portfolio. Don't just try to impress them with the webdesign showcase. Try to
show them how a website for a restaurant had brought more customers to them.
Show them some numbers.
Start building something on the side and try to make it popular. It doesn't
have to be the next big thing. It can be a small news aggregator or a recipe
collection site with some user interaction. Keep your skill set sharp and use
it to market yourself. If you truly made a new product that people love you
won't even need to find work, you'll be working for yourself.
~~~
raamdev
> so offer them to do all the hosting and maintaining for them in exchange for
> free food every week
I do this with a local vegan restaurant. They're the only one in the area and
although I love eating there, they are a bit expensive.
One day I was having trouble getting on their free wireless network, so when I
went to the counter to pay for my meal I mentioned the problem to the owner.
Recognizing that I eat there all the time, she asked if I wanted to take a
look at the wireless router in the backroom. All I did was restart the router
and it worked again. The owner said the $18 meal was on the house for fixing
the wireless.
Now I'm hosting their website and taking care of all tech support in return
for an open tab. I bill the owner but mark the balance as $0 and in return I
never pay for food when I eat there. My good relationship with the owner has
led her to introduce me to other local restaurant owners and now I do work for
them too.
------
jjguy
You need to find the thing that distinguishes you from your peers. My story is
undoubtedly different than yours, but I'll share parts; perhaps it can help
you.
I went to college on a military scholarship. After four years of school, I
spent 6 years in the military. Three critical things came from those years:
contacts, credibility and experience.
After a couple tours, the military's plans for my career and my own ideas
didn't sync up. I left and used a contact to land a nice job doing exactly
what I wished. I floated my resume around, but serious offers only came from
those I knew. I got other offers, but they were in a different class.
I've been with the same organization for several years. It's awesome. I get
calls occasionally from those old contacts, asking if I'm ready to move on
yet. I'm not, but when I do, I'm unlikely to "hit the market." I'll make a few
calls, express some interest and find a home.
I'll say this: your technical skills alone will not land you the _awesome_
work. There are plenty who (claim to) have the same skills; in the world we
live in, it's very difficult to distinguish between us and charlatans without
experience. For me, the military provided the contacts and touch of
reassurance a hiring manager needs to make a decision.
You need to find your distinguisher. If you don't have one, make it. The other
comments here provide plenty of ideas how you can do so.
~~~
edw519
_You need to find your distinguisher. If you don't have one, make it._
Best advice you will ever get here. True for _everything_ , not just freelance
work.
------
menloparkbum
You're doing the right things. It's just very bad right now for freelance
work. I have an artsy-fartsy startup but do heinous "enterprise" style Rails
contracting to make money. My contract was just terminated, because I was too
expensive. I think I was replaced by two others who were charging a lot less
than me. So, I guess if you want to keep working you'll probably have to lower
your rate or else get lucky.
That sounded a bit pessimistic.. I guess for practical tips, Twitter seems to
be a new venue for finding work that actually seems fruitful.
------
ejs
I often think it would be beneficial if HN had some directory that people
could list their skills if they are willing to freelance.
Often times I would like to work with someone more skilled in UI and design
and would rather work with someone who posted on here regularly. Seems like it
would be less risky then say any of the elance/ rent a coder type deals.
I have thought it would be nice if there was a site devoted more to building a
business relationship then just low-ball pricing to get projects done. Maybe I
should just build one, but getting enough people to make it worthwhile would
be the difficult part.
~~~
tocomment
The rentacoder but for long term freelance relationships is a great idea.
Email me if build one. I'd like to help.
------
shuleatt
For one thing it is not obvious how to contact you. Your blog has one
ambiguous link for email but it doesn't even load. Maybe obvious, but you need
to make it simple for someone to reach you.
Nevertheless I am actually looking for RoR help. Hit me up: sam dot huleatt @
yahoo dot com
------
mikeyur
As simple as it sounds, be social. There are countless times where I've been
looking for work and a simple twitter message has resulted in business friends
pointing me in the direction of their friends, and so on.
Use twitter search to check out who is looking for a RoR or PHP dev. This is
how I get most of my SEO work - there's usually a business asking for someone
and I just follow and send them a quick message.
------
tontoa4
Did you try Scriptlance.com, HireACoder.com, or any of those type of sites?
I know there are some cheap people on there, but those that use that kind of
site often know not to hire the least expensive.
Do you have any ideas of your own?
Take this time to create your own startup. I have a ton of ideas that are
self-sustaining if you're interested.
~~~
Zarathu
Yes, I have two startups that are on their way to being very successful.
Though, it'll take 4-6 months before I'm financially free of working at all.
Unfortunately, I don't have that much saved up.
~~~
moe
So you're saying in 4-6 months you'll be free of working at all but worry
about these 4-6 months? Sorry, sounds fishy to me.
~~~
randallsquared
When I read that, I assumed there was an implicit "if all goes well". :)
------
sanswork
If it's an option for you relocate. I'm desperate for PHP/Ruby developers in
Sydney and I know when I was last in Toronto it was the same way. We just
can't find decent developers that aren't already in a great job. Even if
moving isn't an option try finding cities with real shortages and looking if
you can telecommute?
~~~
kungfooey
What exactly is involved in relocating across international borders? Perhaps I
should post this as a Q. I would love to relocate to another country for a
while, but I find the paperwork to be intimidating.
~~~
sanswork
I posted this in your submission as well but just posting it here for anyone
that didn't see that.
It honestly depends where you are and where you are going. I'm from Canada
originally. When I moved to England I had to go to the embassy and fill out a
form and show some birth certificates(I was claiming ancestry). I'm now in
Australia on a working holiday visa. To get that I filled out a form on a web
page and got an email a few hours later with my visa number.
In both cases I found a job when I got there.
------
joshsharp
There was a similar thread not long ago:
<http://news.ycombinator.com/item?id=445776>
And my comment from that thread: <http://news.ycombinator.com/item?id=445836>
------
JacobAldridge
_I'm...asking everyone I know if they know anyone in need_
Good, but: Are you clear on exactly what your ideal client looks like? If
you're not, then this question won't be clear. If the question is vague or
general, it's easier to answer 'no' than to think about it.
You'll get more responses with a clear question like "Know any business owners
with less than 20 staff who want to use their technology better?" than asking
the vague "Know anyone who needs RoR and PHP work?"
(Obviously, you know how to phrase this for your service offering better than
I.)
Also, don't just ask if they know anyone in need. Ask who _they know that may
know_ anyone in need - this will open more doors, and prevent dead ends in
your contact base.
------
nolanbrown23
Put a some info in your profile here; you never know who needs help with their
startup.
Have you tried some of the Gig boards that are out there like 37Signals and
Joel on Software? I've had good luck with those before trying to find a way to
make some spending money.
~~~
sachinag
Seriously. People who are freelancers and don't have stuff in their profile
irritate me. We're always looking for people with skillsets like yours.
~~~
Zarathu
Fixed. :)
------
ejs
I find this very difficult as well (although I am just getting started), but I
can only really blame myself for not being more social (as mentioned here). It
is just much easier to code up more stuff or work on a new project then it is
to really market ones self. I also worry that I focus too much on learning
different things and should instead focus on a just one or two specialties.
I am glad I came across this thread, very good information and advice to
really keep motivated. Thanks again for the great advice HN.
------
iuguy
Think about the things that you've done. Think about the sectors, the
solutions, the requirements.
Find similar things. If you can re-use what you've already done you're halfway
to a profitable solution, but it lets you bid lower than the next guy.
Find your niche. Exploit it. Reuse it. Recycle. The possibilities are endless.
------
bkbleikamp
Network like your life depended on it (maybe it does?). A few good contacts
are worth more than any job board or anything else.
You need to find other good networkers. Once you find them, help them before
they help you. Prove to them that recommending you will make them look good,
too.
------
subbu
Create a profile on LinkedIn (if you don't have one already) and subscribe to
'Ruby on Rails' and other specific groups. I have seen quite a few contracts
(both full-time and part-time) on 'Ruby on Rails' group. May you will find
some luck there. Good luck.
------
davidw
Open source projects are a way to keep yourself visible, although of course
that's not an immediate way to find work. Ask friends, lower your prices...
it's probably tough with the current economy.
------
Trainwreck
Have you tried oDesk or Elance type of venues? There are also Rent-a-coder
type sites as well. Good Luck! Send me your resume in case I hear of anything.
------
rdrimmie
Are there any relevant local meetups or foo/bar/startup/etc camps? Any sort of
gathering where there'll be other local people you can meet and talk to?
------
petercooper
There are lots of people looking for freelance Rails developers. You need to
engage with the community more somehow to ferret them out.
------
known
I suggest you publish a really useful and re-usable .Net/J2EE/Android/FLOSS
(for e.g. memcached) code on your website.
------
edw519
Your existing customers are your most easily converted prospects. Surely,
there's something else they need, right?
------
rubing
Start offering free weekly classes on programming at your local starbucks.
Make it something real general like homepages for small business. Or facebook
profiles, crap like that. Then if somebody wants more substantial private help
or consultation you can charge them for it.
~~~
tjr
On a similar note, look into teaching continuing education classes at your
local community college, or giving presentations at, e.g., ACM/IEEE meetings.
------
albertcardona
I made a website for a tiny open source project of mine, that addressed image
segmentation and 3D visualization of meshes.
I added a link to that web page: "Hire me". And I got hired at a very nice
research institute for an intership. Later I became group leader there.
Bottom line: have something to show, and don't be shy about it.
| {
"pile_set_name": "HackerNews"
} |
The HP-15C was reissued at long last - yodeling
http://majid.info/blog/hp-15c-limited-edition/
======
tetriz
One of the best calculators ever made
| {
"pile_set_name": "HackerNews"
} |
Node.js v0.12 Is Now Available with Improvements to Clustering and Performance - jakerella86
https://strongloop.com/strongblog/node-js-v0-12-released/
======
rmgraham
Time to warm up the test suites and see what the damage is...
~~~
jakerella86
Heh... I think that's why the announcement hasn't been made on Twitter and
such just yet. Waiting to see if they need to immediately release 0.12.1
------
shubhra51
Yay !!! Took a year, but it's here now..
| {
"pile_set_name": "HackerNews"
} |
Profanity and OS projects - should we care? - tuna
http://redmine.ruby-lang.org/issues/5625
Seems like too much free time and the politically correct got its round over the ruby community for good this time. Luckily they are not reading the linux kernel.
======
makecheck
I think a far better action than saying "oh no, swear words" would be to ask:
what code is apparently causing developers to swear and how can it be fixed?
And for what it's worth, when people are offended by mere words I counter with
"I'm offended by censorship", because I am. What is it about certain commonly-
censored materials that makes them so special? Why can't a person just change
the channel or read something else to avoid uncomfortable material? Also, why
are people so much more likely to be angry about swear words (which cause no
demonstrable harm), when things that _do_ cause harm (like wars) are more-or-
less tolerated silently? Makes you wonder.
~~~
tuna
true, code would help there instead of bikeshedding. also it would serve as
guide to anyone following the patch.
------
AndrewDucker
Swear words which are deliberately offensive or pejorative should generally be
avoided.
But there's no reason why flavoursome language can't be used to get across the
developer's feelings about how fucking awful the shit piece of code they've
just had to kludge something into was, and how much they're looking forward to
clearing it up in a later release.
------
eccp
Source code is not only about the implementation, but also about the approach
of the developers to express a solution to a problem. If swearing is part of
that expression, it's OK to me, but I agree that unneccesary swearing, and
being offensive to a certain group or demographic should be avoided at all.
------
deferraz
Lets hope that this douchebag never reads the Linux Kernel source code
~~~
tuna
<http://durak.org/sean/pubs/kfc/> linux kernel fuck count
~~~
deferraz
so much love <3
------
Draconar
such pussies.
------
dextorious
No.
~~~
dextorious
Down-voted, why? For replying succinctly? Does the question merit a larger
reply?
| {
"pile_set_name": "HackerNews"
} |
Ask HN: Beside Bitcoin, what has offered a 1 000 000× ROI over 7 years? - mrb
$1 invested in Bitcoin in April 2010 turned into $1 million. What else has offered a 1 000 000× ROI over 7 years?
======
DrScump
[https://en.wikipedia.org/wiki/Tulip_mania](https://en.wikipedia.org/wiki/Tulip_mania)
~~~
mrb
No, tulip mania wasn't even close: 5,000× returns [1]. More successful
investments are easy to find, eg. someone pointed out in another thread that
the founders seed round of Uber generated 65,000× returns.
[1] The all-time record sale seems to have been about a bulb selling for 5,200
guilders ( [http://www.todayifoundout.com/index.php/2012/12/when-
certain...](http://www.todayifoundout.com/index.php/2012/12/when-certain-
tulips-cost-more-than-a-house/) ); and the pre-bubble price of tulip bulbs was
about ~1 guilder each.
------
mattbgates
Timing is everything.
LinkedIn crashed at the end of 2015, but recovered in early 2016, dropping
from around $250/share to $92 and rising up again to $190. If you took $10,000
and invested it and rode that wave... it is now $195. Would've been a 112% ROI
with about $11k made.
I did take a risk on investing in another company with $10k recently and made
$1000 in a day or two. There are websites out there that help you... its
definitely risk taking with chances of losing a lot of money if you aren't
quick enough, and while it's not technically insider trading... it's more
similar to penny stocks, where timing is everything, and if you have at least
a minimum of $10k to invest, and you ride the small waves.. you can make
thousands of dollars doing that.
Money makes money and with time money can be made. I have a 401k that I can't
touch because I no longer work at the job. I have spoken with financial
advisers about touching it or not touching, and while some suggested I move
it, the fact remains: My money got invested into some really good companies at
early stages that are just not available with any other plans, either with my
current company, or Roth IRAs, so leaving the money in there is just best. The
last time I put money in there was at 4k. A decade later, it is nearing $12k.
Might not sound like a lot to some people, but that is the power of money
making money on itself. I haven't touched it because I can't put anything into
it. Being as I'm still about 30-35 years away from retirement, I'm sure it
will be just fine if I leave it.
Kind of like a Futurama deal... where Fry gets frozen for 1,000 years...
>>The account had contained 93 cents in 1999, but after accruing interest at
2.25% per year for 1,000 years, the balance is now $4.3 billion. (
[https://en.wikipedia.org/wiki/A_Fishful_of_Dollars](https://en.wikipedia.org/wiki/A_Fishful_of_Dollars)
)
~~~
jfaucett
The funny thing about that quote is that 4.3 billion would still probably have
an adjusted value of about 0.93 cents, assuming inflation continued at the
roughly 2-3% a year it has been in most western countries.
------
thiagooffm
Looking at ROI(or any indicator alone) is possibly the worst way to spend your
time, because it doesn't mean anything.
It's such a poor idea that you aren't even factoring the risks in. And can
barely factor it, as it's bitcoin. What is the chance of this entirely thing
breaking down tomorrow as people just give up believing on it? Big chance.
It's completely unusable. I can write a bash script which does more
transactions than bitcoin on a calculator. The blockchain model it uses has no
scale.
As soon as mining becomes more difficult and we hit close to 90% of the coins
and use doesn't increase up(because usage didn't take off, like the prices),
this is all worth 0.
Who has hit the jackpot is the one who sells before this ponzi scheme falls
down and entered early enough.
------
anonymouskimmer
1) Jackpot winning lottery numbers.
2) Possibly various patents.
This is more a matter of the sheer number of people who could become involved
in Bitcoin in a short amount of time (i.e. an artifact of the modern era) than
it is about Bitcoin per se.
------
seattle_spring
1\. Buying random art at garage sales and hoping they were painted by the
famous deceased
2\. Lottery tickets
3\. Slipping at Wal-Mart and suing them for millions
------
gesman
Skills
~~~
wslh
Which skills? The returns in the cryptoeconomy were much higher than the
returns that high skills give.
~~~
meric
Skills in cryptocurrency investment.
------
celticninja
I don't think anything in history has had as good an ROI as bitcoin in the
same sort of timeframe.
| {
"pile_set_name": "HackerNews"
} |
When crisis hits - hanifvirani
http://jacquesmattheij.com/when+crisis+hits
======
tomeric
We run a big online restaurant guide in The Netherlands.
At the beginning of 2009, our income from AdSense (our main source of income)
halved overnight and later dropped to about 25%. We had a little bit of money
in the bank, but not enough to survive for more than a few months.
We immediately focussed on finding and developing alternative sources of
income and those sources have now become our main sources of income and have
enabled us to grow a lot.
Without that crisis, we probably wouldn't have grown as much as we have.
~~~
Luyt
_"At the beginning of 2009, our income from AdSense (our main source of
income) halved overnight"_
Did you ever find out why this happened? I'm also curious which alternative
way of income you eventually found.
~~~
tomeric
We think it was because of the economic crisis. The restaurant sector was hit
pretty hard and that probably caused a lot of companies to stop advertising.
The revenue is now back to it's old levels, but it stayed that way for 6-7
months.
We started a program that allowed restaurants to advertise directly with us.
Made it very easy to try by not having any contracts and being a lot cheaper
than our competitors. We got someone to do sales on a commission-only basis.
He was so good (~ 70% of the restaurants he calls become a customer) that he
is now a partner.
We also added affiliate links to sites where you can order food online, make
reservations, etc.
------
codenerdz
How does one trace money through "connections"?
| {
"pile_set_name": "HackerNews"
} |
Ajit Pai's Big Lie - coloneltcb
https://www.techdirt.com/articles/20171127/01044438683/ajit-pais-big-lie.shtml
======
cwkoss
Ajit Pai is the worst kind of person. Greedy liar bought off by the people
he's supposed to regulate.
~~~
TwoNineA
So like 99% of politicians?
| {
"pile_set_name": "HackerNews"
} |
Government Report Finds Drastic Impact of Climate Change on U.S - blondie9x
https://mobile.nytimes.com/2017/08/07/climate/climate-change-drastic-warming-trump.html
======
diafygi
I work in cleantech, and here's my favorite climate change joke: "They say we
won't act until it's too late... Luckily, it's too late!"
So what can _you_ do about it? Work at a new energy technology company!
Many cleantech sectors are out of the R&D stage and are currently focused on
scale and growth, and we need as many smart people as we can get. There are
lots of companies hiring software engineers (including mine). See my comment
history for links to cleantech jobs.
As for dealing with skeptics, remember that you can't reason someone out of a
place they didn't reason themselves into. Focus on emotion, and don't tell
them what to do (instead, paint an environment where they naturally come to
aligned conclusion).
Here's several ways to work with climate skeptics:
1\. If you know them well and they have kids or grandkids, learn their names
and talk about how life is going to get much harder for them if we don't make
the energy transition. Talk about how many jobs the energy transition will
make (solar already outnumbers coal jobs). Focus on the opportunity for their
kids. Try to paint climate change as a us-vs-the-harsh-fucking-world (rather
than what they currently think of as an us-vs-liberals-and-hippies). This
perspective can make them feel like they are betraying their kids and
grandkids. I've seen this work for family members and close friends.
2\. If they like focusing on the economic/subsidy arguments, make it
competitive and selfish. Talk about how it's going to be their loss and your
gain ("if you're not going to do anything about climate change, that's more
money and work for me, so thanks!"). Focus on building a situation where they
get left behind. Then pile on that more Republicans have installed solar than
Democrats (which is true, by the way), so it feels like their own team is
already on board. Shrug off all the economic and subsidy arguments with a,
"Meh, if you don't want in on it, more upside for me. You complaining just
makes me richer." I've seen this work for tea party friends.
~~~
ramphastidae
> more Republicans have installed solar than Democrats (which is true, by the
> way)
Can you elaborate please?
~~~
freehunter
I have no facts to back this up (hopefully the other guy does) but intuitively
it makes sense to me. If you think about political maps, which areas are
almost always blue, and which areas are almost always red? Cities lean
democrat, and cities also often have higher density living. If I'm in an
apartment, I can't install solar panels. I have no where to install them.
But if I live in a rural or suburban area and have an acre+ of land and a
single-family house, I have a roof and a backyard I can fill with solar
panels. I probably also have a less reliable electricity grid than in the
city, so getting power somewhere else is helpful. I'm also much more likely to
vote Republican.
~~~
dspillett
Also there is a higher proportion of Republican party supporters in some
southern states, where being closer to the equator improves the value
proposition of installing solar cells - because of lower time to paying off
the investment (so there may be a financial gain in having them installed even
if you don't accept the overall climate argument).
~~~
ythn
Also a huge base for democrats are poor minorities (Blacks, Hispanics, etc)
who likely can't afford solar panels as easily.
------
jpao79
Does this proposal from a conservative group represent a good solution?
[https://www.nytimes.com/2017/02/08/opinion/a-conservative-
ca...](https://www.nytimes.com/2017/02/08/opinion/a-conservative-case-for-
climate-action.html)
[https://www.ted.com/talks/ted_halstead_a_climate_solution_wh...](https://www.ted.com/talks/ted_halstead_a_climate_solution_where_all_sides_can_win/reading-
list)
If I understand it correctly, if it is implemented correctly, a few benefits
are that it would:
\- Reduce the validity of any climate change denier claims that climate change
is actually a political scheme to redistribute wealth from the developed world
to the rest of the developing world.
\- It would also reallocate carbon tax proceeds towards making the developed
world into a leader in climate change prevention solutions.
Would love to hear other people's opinions.
~~~
aoeusnth1
A carbon tax is the single best possible carbon policy. If implemented well,
it
\- simultaneously provide the mosts efficient incentives to reduce carbon
emissions by shifting the cost onto exactly the people who are offending.
\- and provides the funds to compensate the victims of climate change (every
human), plus spare change for fundamental research into new Green tech which
too unproven to be viable as a startup (would nuclear power ever have been
created from scratch by the market?).
It also makes sense to tax SOx, NOx, and other air pollutants for exactly the
same reason. However, the time scale and magnitude of those problems are
nowhere near as dire.
~~~
ehnto
I feel as though you may be implying the carbon tax is applied to industry and
in policy that's correct, but in practice the carbon tax is passed onto the
consumer. Sometimes unashamedly so. I'm not saying it's a bad thing mind you,
less consumption is what we need.
Australia trialled this. I say trialled, because our government has been such
a flip flop of agendas (and indeed leaders) for nearly a decade and it was
only around for 3 years before being repealed. No doubt we'll see it again
soon, and I look forward to rehashing the same tired debates, albeit in
slightly warmer weather, when that occurs.
~~~
nl
Of course it's passed on to the consumer.
Then some company works out how to do the same thing in a less carbon
intensive way, and it's cheaper.
That's the whole point. This isn't fixable without pain, no matter how people
pretend.
~~~
specialist
_" This isn't fixable without pain..."_
Reducing waste (CO2) will boost profits.
[https://en.wikipedia.org/wiki/Muda_(Japanese_term)](https://en.wikipedia.org/wiki/Muda_\(Japanese_term\))
Industry is asking for a carbon tax. There are few holdouts, for political and
personal reasons. Namely, fear and ignorance.
~~~
wbl
If it did, they would already have.
~~~
thinkfurther
If short term thinking, externalizing costs and psychopathology would not
exist, maybe. But not as is.
------
toxican
Does anyone else get irked when articles use photos of nuclear power plants
when talking about pollution or climate change? I'm certainly no expert, but
my understand was that the 'exhaust' from nuclear plants is just water vapor
and with the exception of finding a place to store spent rods, it's an
incredibly green source of energy and has little to no bearing on climate
change?
~~~
rory096
That's a coal plant. And not just any - the largest greenhouse gas emitter in
the country.
[0]
[https://en.wikipedia.org/wiki/Plant_Scherer](https://en.wikipedia.org/wiki/Plant_Scherer)
~~~
toxican
oh, fair enough! I didn't realize that style of stack was used for anything
but nuclear.
------
Fej
At this point, mass panic might be more effective than mass ignorance.
~~~
mirimir
At this point, I'm not sure that anything will make much difference. Or at
least, for anyone now alive. There's just too much inertia, at all levels.
~~~
simonh
There's no way to change the directional trend, but there are lots of things
we can do to affect it's slope. Many of these things are also worth doing
anyway for reasons such as energy security, resource and environmental
preservation, reducing pollution, protecting biodiversity, etc. I do not
believe crash course change in the global economy and our technology base is
possible or desirable, were just going to have to live with and manage many of
the negative consequences of climate change, but we can achieve a lot with
sensible, moderate and achievable environmental policies provided they are
pursued determinedly and consistently.
~~~
_up
We can also cool the earth via Sulfur Injection in the Stratosphere (like
Vulcan eruptions demonstrated). German Spiegel[1] had an Article a few weeks
ago that also mysteriously threatened international sanctions or war to
countries who try that.
[1] [http://www.spiegel.de/wissenschaft/natur/klimawandel-
geoengi...](http://www.spiegel.de/wissenschaft/natur/klimawandel-
geoengineering-als-plan-b-fuer-eine-zu-heisse-erde-a-1159027.html)
~~~
kodfodrasz
Wouldn't that result in acid rains eventually?
------
RickJWagner
I see arguments here that people can readily feel a change.
I have to admit, I don't see it. It's been an unusually calm summer where I'm
at. We haven't had a summer with several days over 100F in quite a few years.
If anything, it's been less hot.
But I'll surely give the report a read. It is an important topic.
~~~
toxican
Only thing I could really point to is a number of incredibly mild winters a
few years in a row. But even then, I was under the impression that climate
change wasn't particularly measurable on a year-by-year scale. Maybe I'm
wrong.
~~~
Goronmon
Just because the individual changes aren't going to be noticeable year over
year, doesn't mean the cumulative changes won't hit tipping points for
noticeable effects to occur in certain cases.
Just like people won't notice the sea levels changing each year. But at some
point, flooding is going to go from a rare occurrence to a regular occurrence
once the sea level raises past a certain point.
------
geiseric
I wonder how valid this is?
[http://www.news.com.au/national/western-australia/miranda-
de...](http://www.news.com.au/national/western-australia/miranda-devine-perth-
electrical-engineers-discovery-will-change-climate-change-debate/news-
story/d1fe0f22a737e8d67e75a5014d0519c6)
------
guscost
> The authors note that thousands of studies, conducted by tens of thousands
> of scientists, have documented climate changes on land and in the air.
The enormous effort put toward finding "confirmations" of the hypothesis has
always been a big reason why I'm reluctant to trust the authorities in this
case. I don't see the point of going through this again. Where are the
falsifiable predictions? Will the Arctic Ocean be ice-free next month? We're
back to point number one from Karl Popper's essay:
"It is easy to obtain confirmations, or verifications, for nearly every
theory- if we look for confirmations."
~~~
kristopolous
If you drive blindfolded do you know exactly how your car will be dented or
precisely where the collision will take place?
Does not knowing these answers make the activity fundamentally safe and
concern about blindfolded driving to be alarmist?
It's certainly possible to see something as absurdly dangerous without having
crystal ball level predictive accuracy.
~~~
guscost
Option A: This crisis is so important that we don't have time to wait for
science stuff like falsification.
Option B: This crisis is known to serious scientists, and everyone who doesn't
agree is a knuckle-dragging moron.
You can only pick one of those options...
~~~
kristopolous
That's the argument tobacco companies used. They'd find one counterexample of
someone who smoked 70 years and say "Aha! No cancer here! Tobacco is safe!"
I mean seriously, find a new strategy, that one is from the 60s.
------
mirimir
One trusts that the National Climate Assessment will also be available
publicly, one way ot the other.
~~~
ryanchoi
AFAIK drafts are already viewable (if this is what you meant?), ex:
[https://www.nytimes.com/interactive/2017/08/07/climate/docum...](https://www.nytimes.com/interactive/2017/08/07/climate/document-
Draft-of-the-Climate-Science-Special-Report.html)
With the public draft already released, I think it would be especially
surprising if the administration tried to impose non-trivial changes to the
document.
------
tradersam
Could we get the non-mobile link?
~~~
dovdovdov
[https://www.nytimes.com/2017/08/07/climate/climate-change-
dr...](https://www.nytimes.com/2017/08/07/climate/climate-change-drastic-
warming-trump.html)
~~~
simonebrunozzi
And this is the actual report:
[https://www.nytimes.com/interactive/2017/08/07/climate/docum...](https://www.nytimes.com/interactive/2017/08/07/climate/document-
Draft-of-the-Climate-Science-Special-Report.html?smid=tw-
nytimes&smtyp=cur&_r=1)
------
dogruck
Where can I read the report, and what is the list of scientists?
~~~
aaronbrethorst
[https://www.nytimes.com/interactive/2017/08/07/climate/docum...](https://www.nytimes.com/interactive/2017/08/07/climate/document-
Draft-of-the-Climate-Science-Special-Report.html?smid=tw-
nytimes&smtyp=cur&_r=1)
~~~
dogruck
I had to lol at "there is significant possibility of unexpected changes."
------
ethbro
How inconvenient.
------
stanislavb
Don't say...
~~~
stanislavb
" The average temperature in the United States has risen rapidly and
drastically since 1980, and recent decades have been the warmest of the past
1,500 years, according to a sweeping federal climate change report awaiting
approval by the Trump administration."
i.e. if Trump's administration does not approve it, it does not exist :D
~~~
mirimir
If people care, stuff leaks :)
------
d--b
At this stage, this is a bit like saying: new report finds evidence that God
did not create the world in seven days. It's no longer a matter of science,
it's a matter of people choosing not to believe in science.
~~~
deckiedan
I absolutely agree.
As a side note: Its 6 days, not 7. Day 7 (the Sabbath) was for resting.
As a longer thought: God, as a omnipotent being, obviously doesn't need to
rest, and given the idea that he (for lack of a better pronoun) is essentially
keeping the universe running himself, the whole concept of 'God resting' is
obviously (to me, and many others) poetic. Looking at the rest of the Genesis
creation story through 'poetic narrative' lenses:
From the beginning of the universe until the start of human written history,
we can divide it up into Eons (non-specific but LONG periods of time):
Eon 1: \- The universe was 'formless' and chaotic. \- Pure energy / light and
darkness / vacuum / void become separate.
Eon 2: \- The planets and other 'heavenly bodies' or galaxies start to spin
together into units. \- Planetary atmospheres form. (The separation between
'waters below' (the unknown depths of the sea) and 'waters above' (the vast
'ocean' of space') from a ).
Eon 3: \- Focussing on Earth, the planet surface began to stabilise,
continents appear. \- Plants and other 'basic' forms of life begin to show up
and spread all over the planet.
Eon 4: \- The moon shows up, the atmosphere clears up a bit, stars are now
visible, the earths spin is now stable re. Day and Night.
Eon 5: \- Animals! Firstly water based, then birds. Maybe huge birds
(dinosaurs?) No non-bird land-dwellers yet.
Eon 6: \- Land based animals, 'finally' humans showing up.
Eon 7: \- Now. Beginning of written histories.
The above pattern is a pretty strict interpretation of the first chapter of
Genesis, with most of the poetic stuff stripped out. It's kind of interesting
how much of it does kind of map to our current understanding of the beginning
of the universe and our planet.
What do you think?
~~~
coliveira
Typical reinterpretation of Genesis 1. Unfortunately, the text also says: "it
was the evening and the morning, the first day." i.e., the text goes out of
the way to affirm that this was the task of a single day, not of an eon.
~~~
deckiedan
Well, kinda. What is an evening or morning when there is no sun, night, day
time? More likely it's just a poetic turn of phrase. What I find interesting
is you can stick to "it's poetic, but modern scientific understanding can fit
in happily" And aren't forced into saying, "science and Genesis are
incompatible".
~~~
logfromblammo
If you're going to claim poetic turn of phrase, you really have to look at the
text in its original languages. There are many examples of strained
translations or outright mistranslations for religious texts.
The word used in the original that was translated into English words for day,
night, morning, and evening could very well be "an unspecified subjective
length of time", "literally 86400 seconds", "literally 43200 seconds", "the
timespan for which any portion of the sun is visible in the sky", "the
interval between waking and going back to sleep", etc.
The objective reality is that Genesis is a myth written by primitive
screwheads that predated the invention of scientific inquiry. Any similarity
to any extant theories on the origin of the universe are purely coincidental,
highlighted by human brains that are hardwired to find patterns and meaning
even where genuine relationships do not exist. There is no shame in having a
religion that makes no sense scientifically, provided that you can keep it
separate from any matters that require rational thought grounded in observable
reality.
Let the religion be what it is. Attempting to reconcile it with scientific
theory is pointless, and ultimately a waste of time, because science may just
discard that theory and take up another any time new data become available.
Indeed, theories like the Big Bang only became widely known _because_ they are
remotely reconcilable with Genesis. It isn't the only cosmology theory capable
of explaining all the available evidence, nor is it necessarily the best one.
Reconciling religion with science makes as much sense as explaining the
biological basis for Harry Potter.
It does not matter if religion is made-up nonsense. The important thing is the
tribal sense of community one gets from knowing all the same nonsense as
everyone else, and the artistic inspiration one may draw from it.
Believing one's religion is the literal truth and also believing that
scientific inquiry is the best method at our disposal for understanding and
affecting our universe is no more difficult than believing that Star Wars is
set a long time ago, in a galaxy far, far away, while also believing that Star
Trek is set a century or two in the future, in an alternate-history version of
our own galaxy. We can simultaneously believe that all fantasy universes are
separate, and never shall any two meet, and that they all somehow link
together through the Stargate inside the Dark Tower.
Science and Genesis _are_ incompatible. But they _don 't need to be_
compatible.
------
microcolonel
> _WASHINGTON — The average temperature in the United States has risen rapidly
> and drastically since 1980, and recent decades have been the warmest of the
> past 1,500 years, according to a sweeping federal climate change report
> awaiting approval by the Trump administration._
If that's the case, then wouldn't it already be born out in other widely
available temperature datasets? No credible person denies that the global (and
U.S. local) mean temperature has increased, this is not news.
> _The draft report by scientists from 13 federal agencies, which has not yet
> been made public, concludes that Americans are feeling the effects of
> climate change right now. It directly contradicts claims by President Trump
> and members of his cabinet who say that the human contribution to climate
> change is uncertain, and that the ability to predict the effects is
> limited._
These are entirely separate claims. The author of the article is saying that
the United States are warmer; then implying that the change is entirely man-
made and detrimental to make a political point (in this case, a hit against
President Trump, though I suppose it's a step in the right direction that NYT
are now allowed to refer to the President as the President). (Edit: I should
clarify that I'm talking about the link between the two clauses in this
paragraph, which makes it seem like one supports the other when this is not
the case)
> _and that the ability to predict the effects is limited._
It _is_ limited, the report details the limits, as do many other great
sources. The climate models we have are about as good as the economic models;
that is to say, they're basically useless for genuine predictions. They do not
fit historic data without piles of corrections, some of which are dubious.
There is work to be done.
If you have data to back up your points, show the data. If you are making a
point which is not supported by the data, don't use slight of hand to make it
seem like it is.
The reason that there are so many people skeptical about the alarming claims,
is because the presentations have been so dishonest and manipulative. Public
figures frequently grossly overstate the certainty of statements which are not
really settled, and some climate scientists and academic administrators have
been caught basically ganging up on people who do not present alarming news.
I understand why some of you feel, as Fej says elsewhere in this thread, that
"At this point, mass panic might be more effective than mass ignorance.", but
it's important that we be honest in presenting what we know to the public.
Every time you present an opinion as a fact, somebody somewhere no longer
trusts you, and those people will be vocal and active in letting people know
that you've been dishonest.
~~~
nl
I think that at this point if you don't believe climate change is happening
and is man made and is significant then it is unlikely anything is going to
convince you.
_If that 's the case, then wouldn't it already be born out in other widely
available temperature datasets?_
It is. Really.
There's even a nice dataset on Kaggle you can play with if you like:
[https://www.kaggle.com/berkeleyearth/climate-change-earth-
su...](https://www.kaggle.com/berkeleyearth/climate-change-earth-surface-
temperature-data)
_If you have data to back up your points, show the data_
The data is linked, and there is plenty more data out there.
Enjoy.
~~~
yaddddda
"Cleaned" data. Naturally.
~~~
nl
If you want to do the cleaning yourself, the "uncleaned" data is here:
[http://berkeleyearth.org/data/](http://berkeleyearth.org/data/)
_Source observations are provided as originally reported and will contain
many quality control and redundancy issues. Intermediate data is constructed
from the source data by merging redundant records, identifying a variety of
quality control problems, and creating monthly averages from daily reports
when necessary._
You can choose to use breakpoint adjusted or not, the data is all there.
------
cool_look
It got hotter until 1998 and plateaued until today 2017+, occasionally setting
small new highs (0.1C when margin for error is 0.4C).
That was already accepted and should not be trumpetted as further "proof".
------
mnm1
The conclusions here are obvious to anyone that's been living in the US in the
last decade or two. It's not that difficult to see/feel the changing weather
patterns. So why does it need approval? This is science. What kind of science
needs approval? If the government agencies want to dispute this, let them put
forward a different hypothesis from the data. This authoritarian monopoly that
various government agencies have on science has got to stop. It's not just
climate change. Facts like cannabis being a safe substance, lead being
dangerous, etc. are/were ignored for decades. It seems to me government funds
studies and then ignores their conclusions. This is clearly not in the
interest of society. At the very least it's an absolute waste of money. Will
the government ever represent the people and their interests or is it just too
far gone for that to the point that we're stuck with the interests of a few
assholes controlling and ruining everything?
~~~
s_kilk
> So why does it need approval? This is science. What kind of science needs
> approval?
One word: Capital.
There's a hell of a lot of money tied up in the carbon industry, and
maintaining the status-quo for that section of the capital class is predicated
on not acknowledging climate change.
------
jrapdx3
I'm certainly not an expert in the domain of "climate change", but it doesn't
appear to be difficult to find reviews of the subject that come to different
conclusions than reached by the NYT.
For example, here's a recently published paper authored by qualified
individuals and the conclusion endorsed by several reviewers [0]. Bottom line
was that "Global Average Surface Temperature" data was not credible and that
"... it is impossible to conclude from the three published GAST data sets that
recent years have been the warmest ever-–despite current claims of record
setting warming."
This analysis and others leave the impression the subject of climate is not
"conclusively settled" nor without legitimate controversy as to how data is
interpreted and used for predicting future trends.
It's a shame that important research has become a "football" kicked around
wildly for political advantage rather than being left in the realm of
authentic scientific study for as long as necessary to understand the
processes of Nature that we call "climate".
[0] [https://thsresearch.files.wordpress.com/2017/05/ef-gast-
data...](https://thsresearch.files.wordpress.com/2017/05/ef-gast-data-
research-report-062717.pdf)
~~~
nl
It's published on wordpress.com, non-peer reviewed etc.
There is a range of credible opinions on some aspect of climate change (for
example, the impact of water vapor around cities on measurement). It's
probably worth concentrating on the ones which have at least been peer
reviewed.
~~~
seren
Googling the author's names, you'll quickly find a snopes article in the first
results:
[http://www.snopes.com/climatology-fraud-global-
warming/](http://www.snopes.com/climatology-fraud-global-warming/)
~~~
jrapdx3
True enough, I didn't check out the authors or those endorsing the report. The
report wasn't from a peer-reviewed journal, but then neither is the NYT or
Snopes.
The analysis could be considered on its merit. I'd leave that to people better
qualified in that field than I am.
We'd expect bias, that's entirely normal in all research. But the deep
polarization of the scientific community considering climate data and findings
is symptomatic of the absurd political influence on the field. The extreme
level of viciousness surrounding climate research has to render _all of it_
suspect in any honest observer's mind.
| {
"pile_set_name": "HackerNews"
} |
Google Responds To FTC With “You’re Looking For What, Exactly?” - yanw
http://www.marketingpilgrim.com/2011/06/google-responds-to-ftc-with-%E2%80%9Cyou%E2%80%99re-looking-for-what-exactly%E2%80%9D.html
I'd love for law knowing person lurking here at HN to explain why exactly does the FTC think they have anything near a case here, I do concede my Google fanboydom but other than they were pressured by Google competitors to act there doesn't seem to be any merit to this, right?
======
wccrawford
That article is pretty biased. It seems to say that Google is Good and nothing
it can do is wrong. It even claims that it had some hand in helping us weather
the economics hardships of late...
Other than employing people, which every company does, I don't see how they
made any difference. Maybe I'm just ignorant when it comes to that, though.
They also go out of their way to make the FTC look like bad guys. No, the FTC
has had complaints, and it is doing it's job by looking into them. It has to.
And Google appreciates that position and is complying. I really don't see any
bad blood between the FTC and Google, so why this blogger is so hot under the
collar is something I have to question. It's not like the blogger could know
any more about the situation than the FTC does at this point.
------
thisuser
Article claims: \- Google should canonized (stock market as implied canon?) \-
Anti-trust legislation is merely political whimsy \- Corporations don't have
inherent structural problems, all problems are caused by individuals
Can we keep this shallow business major ideology crap off of HN? It is
simplistic corporate knob slobbing. I expect a more empirical stance in this
community.
~~~
yanw
How about this then:
[http://techliberation.com/2011/06/24/the-ftc-makes-its-
googl...](http://techliberation.com/2011/06/24/the-ftc-makes-its-google-
investigation-official-now-what/)
Either way the investigation is lacking in merit.
| {
"pile_set_name": "HackerNews"
} |
Countries with poor human rights records spend millions on public image (2015) - doener
https://www.publicintegrity.org/2015/12/17/19051/us-lobbying-pr-firms-give-human-rights-abusers-friendly-face
======
buyx
PR firms seem to do a lot more than foreign lobbying and propaganda, and seem
to be engaged in active manipulation of clients' populations.
In South Africa, UK PR firm Bell Pottinger was engaged by the Gupta family to
promote their (widely reported to be corrupt) interests. Direct protests
against the PR firm, including by South African expats in the UK, and SA-owned
clients led to Bell Pottinger dropping the Guptas. Nonetheless its been widely
reported that Bell Pottinger's strategy included fomenting racial division in
order to divert attention from President Jacob Zuma and the Guptas. By many
accounts, they have succeeded.
I'm sure that this sort of thing has been going on for decades, but it is
notable that the victims of a PR firm (the South African public) were able to
turn the tables and force a first-world PR firm into damage control mode.
~~~
skummetmaelk
Things like this make me wonder if we need a morality police now that poor
morals have no social consequences anymore.
~~~
rhizome
This exists in the form of the foreign and trade (and occasionally military)
policies of other countries toward yours.
------
djcjr
US spends millions on public image too, no?
~~~
MereInterest
[https://en.wikipedia.org/wiki/Whataboutism](https://en.wikipedia.org/wiki/Whataboutism)
~~~
ldp01
I _think_ the point he's trying to make is that countries spend millions on
public image regardless of their human rights records. There isn't a
meaningful correlation until we have examples of countries with good human
rights records which aren't spending millions on their public image.
~~~
djcjr
Yes.
------
gonmf
And Israel is notoriously omitted.
------
doener
This article is from 2015.
The mentioned Qorvis/MSLGroup now runs e.g.
[http://www.arabianow.org/](http://www.arabianow.org/) (also in German:
[http://www.arabianow.de/](http://www.arabianow.de/)) which promotes the
brutal regime of Saudi Arabia:
"This content is distributed by Qorvis MSLGROUP on behalf of the Royal Embassy
of Saudi Arabia. Additional information is available at the U.S. Department of
Justice."
| {
"pile_set_name": "HackerNews"
} |
High Tech Angel Panel: 2010 Trends at Hacker Dojo Jan-18-2010 - skmurphy
http://fountainblue.biz/resources/hightech.html
======
skmurphy
Chance to meet these panelists. Tickets $21-42 in advance
Bill Reichert, Garage Technology Ventures
Jim Connor, Board Member, Sand Hill Angels
Edward Esber, Angels Forum and Halo Fund
Ann Miura-Ko, Partner, Maples Investments
Ron Weissman, Band of Angels
| {
"pile_set_name": "HackerNews"
} |
An old IBM null hardware device to handle null-pointers - DyslexicAtheist
https://twitter.com/thegrugq/status/1040615151605432320
======
eesmith
??? That makes no sense. Is it a joke? Or, like a left-handed smoke shifter,
something meant to poke fun at the naive and gullible?
| {
"pile_set_name": "HackerNews"
} |
Geocoder: The Missing PHP5 Library - couac
http://williamdurand.fr/2012/05/31/geocoder-the-missing-php5-library/
======
guillaumepotier
Nice work!
| {
"pile_set_name": "HackerNews"
} |
Solving a Sudoku using SQL - silkodyssey
http://technology.amis.nl/blog/6404/oracle-rdbms-11gr2-solving-a-sudoku-using-recursive-subquery-factoring
======
arnorhs
Another fine evidence of how bloated Oracle is. Sorry, that's just my opinion.
Why would you want to be able to do something like this in your datastore?
Maybe a database-admin really wants to be a programmer?
| {
"pile_set_name": "HackerNews"
} |
How my life was changed when I began caring about the people I did not hire - chl
http://brookeallen.com/pages/archives/1234
======
BrookeTAllen
Hi, this is Brooke, the original hiring manager. I'm new to HN so please
excuse me if I violate protocol.
I agree, life is about treating people well. However, although I find hiring
is probably the single most satisfying thing I did on my job, it was very hard
emotionally because in the case of nearly everyone I don’t’ hire it is because
they say “NO” to me, and boy, rejection hurts. But at least I have a job and
my candidates usually don’t.
More later but first…
If my site is unresponsive there is this on slideshare:
[http://www.slideshare.net/BrookeAllen1/brooke-allen-has-a-
be...](http://www.slideshare.net/BrookeAllen1/brooke-allen-has-a-better-way-
of-hiring) I've generalized my approach to hiring all sorts and describe it
here: [http://qz.com/88168/how-to-hire-good-people-instead-of-
nice-...](http://qz.com/88168/how-to-hire-good-people-instead-of-nice-people/)
…
When I'm lucky enough to talk to programmers I'll describe it this way...
I don’t want to be stuck in Von Neumann’s bottleneck so rather than me
processing candidates in series with the question “Who do I want to hire” I
take an OO approach and send a different question, “Who wants to work for me?”
to my candidates so they can work on it in parallel.
Since hiring is an elimination process I let them eliminate me in the first
rounds. I don’t say “no” but I have to take a lot of it, which can be hard on
the ego, particularly if I judge people too early and start to want one person
over another. Desire is at the root of suffering. (Any fans of the move The
Tao of Steve? Formula for getting the girl: 1) Be desireless. 2) Be excellent
in her presence, 3) Let her desire you.)
I try to be the most flawed (e.g. honest) but-striving-to-be-excellent person
I can be in front of my candidates and hope they will be the same for me (and
magically they are). If we’re not going to be who we are before we start
working together who do we plan on being afterward?
Because eliminating candidates is the name of the game, I concentrate on the
negatives and that way there are only positive surprised later. Arguably many
of my “best” candidates might eliminate themselves, but I’m not looking for
the best – I can never afford them anyway – I am looking for the most
appropriate for my budget, which I state early on and is almost never subject
to negotiation. You cannot increases your desirability to offer to work for
less, and if you are worth more than I can afford than I’m sorry, but I cannot
afford you.
I want what I call hidden talent; those good at doing a job but bad at getting
one. After all, the last thing I want you to be good at on my job is getting
the next one. I'll help you find a better job before I hire you because
afterward we've got to hunker down and get some friggin' work done.
Because I form an intentional temporary community of my candidates, and task
them with something hard but meaningful that benefits them (like learning a
new skill and/or helping each other find work) then by the time I say “yes” to
someone everyone else agrees with the decision. In fact, in 10 years only once
did a person tell me he thought I had made a mistake by not hiring him and the
other candidates were so outraged they jumped all over him and one – who
happened to be a lawyer – offered to defend me pro bono if he tried any funny
business.
I never heard from him again but it is my great pleasure to say he is an
exception in that regard and I count a few of the people I haven’t hired among
my friends. This is a wonderful side-benefit because as I get older it is
harder to make new friends, and it is certainly unwise to treat employees as
friends as some do.
I seldom tell individual candidates what they did wrong, not because I am shy,
but because it can be hard to take and I’m fairly tactless. However, I will
offer a class on how to find work in which I anonymize specifics enough so as
to benefit those who can identify themselves. Also, most people don’t do
anything seriously wrong other than be unqualified or unlucky; no shame in
that.
More later, if you’re interested.
After 30 years I’ve retired from the capital markets and they will do fine
without me, but the markets for human capital are severely broken. Because I’m
not ready to die, stop working, or give up on having a life's purpose, if you
would like me to help you crack this nut then please do not hesitate in
contacting me.
~~~
reledi
_> hidden talent; those good at doing a job but bad at getting one_
I really like this. If you're bad at getting a (good) job then employers
safely assume you would also be bad at the job - it's too risky otherwise. But
often that isn't the case, because there's a lot of "hidden talent".
What can we do to give those people a fair chance? We need effective ways to
discover hidden talent. The process you described worked for you, but it
doesn't seem practical. Too time consuming for both the employer and job
seekers, and not rewarding enough for those who don't get a job out of it.
~~~
namelezz
Are there ways to help those talents get together and start their own
companies? Otherwise, they may go to interviews and keep getting rejected.
~~~
Retra
Do you think those people who are not good at selling themselves are going to
be good at convincing people to buy their stuff?
~~~
dllthomas
That depends on why they're bad at selling themselves. For instance, if they
get ridiculously self-conscious when the conversational focus is on _them_ ,
that shouldn't get in the way of selling something else.
~~~
owennoah
Hi, I'm Noah and I head BD for Better Work World, the organization I have
started with Brooke to help firms hire the way he did. As for the above
comment, this is true but the larger point is that, if the job isn't
explicitly a sales position or doesn't require gaining internal agreement
(like, say, many managerial roles)`one's ability to sell one's self in an
interview is somewhat irrelevant, wouldn't you agree? Think about it: if you
are a coder and happen to have several social anxiety issues, you would
probably be an awful interview. But who cares? The market for coders is so hot
it seems that has been largely accepted, albeit implicitly, but for less hot
positions, not so much. We believe candidates win and hiring managers win when
you focus on getting people to DO the work as opposed to talk about doing the
work. When Brooke hired this way he found people he would have never hired
through reviewing resumes, so thats a win for both of them, and those whom he
did not hire-- many of whom had been unemployed-- would usually quickly find
jobs elsewhere because they were given the opportunity to do relevant work,
network, etc. To me, that beats the standard, "what's your biggest weakness?"
line of questioning any day of the week.
------
sekasi
I've done a LOT of interviewing, recruiting and ultimately a lot of saying
"no" to people.
Over the years I've landed on a series of personal rules on how to do just
that.
1\. Always explain rationale around the No, to help them improve 2\. Always
let people down gently reinforcing positive notions as well, you never know
what state of mind they are in. 3\. Always respond to requests for more
information
This takes me a lot of time in my professional life, but it's making me a
happier person. Ultimately, it's people's lives you're dealing with. You don't
owe anyone anything, but life is about treating people well.
~~~
kazinator
Then there is the perspective from having heard "no":
1\. Never believe anyone's rationale regarding their "no". They acted on
instinct, and made up a clever story to afterward to convince themselves it
was a rational decision. Or worse: it was some prejudice that they are
consciously covering up. Or perhaps some internal reasons that they don't want
to discuss with outsiders like sudden news that affects all hiring activity
(but this news can't be made public yet: even the fact that there is such
news).
2\. Don't take it personally.
3\. Never press people for more information: waste of time.
~~~
RobertKerans
I don't do the actual hiring, but sit in in one of the two interviews, and as
a team we carefully discuss each candidate. We've got a good team, the work
environment & people are great, hiring process is solid enough. And we all
agree that, _almost_ without exception, we can tell within about thirty
seconds of meeting them whether someone is likely to be hired. I _assume_ this
is overwhelmingly common? Bar sending a polite rejection letter, we would
often prefer not to explain the actual whys[1], as often they are personal.
Kudos to the OP (and yeah, it would make you feel good), but I'd tend to agree
with you on this.
[1] that being said we always, always try to give some constructive feedback
if asked.
~~~
lsiebert
I, seriously, don't understand how this works, unless your candidates
appearance and accent are your main tools for judging a candidate. I would
prefer to think that's not the case. If you were teaching a new member of the
team to make such a decision, what would you point to?
What's more important, is I don't understand how anyone could possibly improve
their 30 second impression.
I guess it could be that you believe this to be the case, and are remembering
wrong. Why don't you note this down after 30 seconds, and then check it only
after you make a decision to see if you were correct?
~~~
RobertKerans
Yes, I admit there is an element of hyperbole (for 30 seconds probably read
30seconds - 5 minutes depending, and that alters if a candidate [ie for a
junior position] is nervous and it takes time to get them to relax somewhat).
Appearance is important, and I've never been in an interview situation where
it wasn't? Unless you're insinuating choice based on ethinicity (more aimed at
_pmf_'s response to your comment). Which is completely irrelevant, as are
accent/sex/other discriminatory factors that make zero difference to how
someone is likely to work within a team.
As I've said in other comments, there is a serious element of external
preselection based on geography and company sector, there's nothing
particularly underhand going on.
~~~
king_jester
> Which is completely irrelevant, as are accent/sex/other discriminatory
> factors that make zero difference to how someone is likely to work within a
> team.
This is just plain ignorant. Every single place I have worked has had its
share of everyday sexism and racism, and that includes how current employees
act in hiring interviews. You claim to not notice these things, but what you
are saying is that you don't consider those things valid differences that may
affect how someone perceives your team or work environment. How can you ever
confront issues in your workplace by shoving your head in the sand?
------
JeremyMorgan
The first time I got a front page link to my site on HN, it did this exact
same thing, which prompted me to move away from Wordpress. Static HTML ever
since.
But to comment on the article, I think this is a fantastic idea. I do wonder
though how he found so many enthusiastic people. Maybe it's just a new era,
but I have a hard time finding people who even want to do a 1 hour coding
challenge. He got these folks who were willing to learn something, and build
and spend DAYS on it? It's awesome but it seems unlikely these days.
Taking that kind of time to choose the right person, then helping the other
people network with other APL folks... that just spreads good vibes all
around. I would like to see the "care more" trend spread in our industry. Even
now with a programmer shortage companies are still unicorn hunting and making
people jump through stupid hoops for jobs.
~~~
FooBarWidget
My Wordpress blog used to go down because of HN. I fixed that as follows.
1\. Use the Wordpress supercache plugin.
2\. Put Apache behind Nginx, and limit the number of Apache processes to ~6.
This way you're effectively using Apache as a "PHP app server", simulating an
architecture similar to Passenger/Unicorn. Nginx acts only as a buffering
reverse proxy, shielding Apache from slow clients.
Why this instead of running Wordpress/PHP through Nginx using php-fpm? It's
because Apache is just easier: mod_rewrite rules work automatically, etc.
~~~
nilved
This is first time I've seen the words "Apache is just easier" in that
arrangement. I think php-fpm is significantly easier to set up than Apache and
expect it to be more performant with less resources.
~~~
okaram
This probably depends more on experience, and which OS/platform you're using;
although I don't do it a lot, I've configured Apache servers several dozen
times, whereas I've only done nginx a couple of times, so it is 'easier' for
me.
Also, on ubuntu (and centos, but haven't used it in a while), it is something
like 'apt-get install apache-mod-php' and everything is there :)
------
shortcircuit01
This story reminds me of how broken software engineer interviewing is. Imagine
if a company decided to hire software engineers by giving them five 6-sided
dice. Then they have to come to the company building and roll each dice once
every hour. And during that hour they have to dance and sing in front of
someone while being recorded. If they roll all 6 on all 5 dice, their dancing
and singing will be judged by the committee! And if the committee likes their
performance they might get the job! The acceptance rate is 0.01%, the company
is so elite. And this company is also complaining about a software engineer
shortage. They wish they could find more good engineers!
It's pretty obvious which company (or group of companies) I'm referring to.
The interviewing process of these companies has done great harm to the
software industry. And now they're trying to do further harm by using it as an
excuse to get cheap foreign labor to reduce salaries.
~~~
bvanslyke
Palantir?
~~~
selimthegrim
I believe he or she is talking about Google.
~~~
twright0
Google's acceptance rate is well above .01%, just using basic reasoning.
Google employs tens of thousands of engineers, which means they would have had
to reject hundreds of millions of candidates for the role of software
engineer.
~~~
theatgrex
You're hired!
------
smacktoward
I wonder how much of this kind of thinking can be traced back to a persistent
startup-culture problem: the delusion that the people who work for you are, or
even _should be_ , your friends.
If that's the lens you're looking at candidates through -- as people
auditioning to be your friend -- of _course_ you'd feel you're obligated to
help them through their job search! That's what friends do for each other.
But the people who work for you -- and even more so, the people who have only
_applied_ to work for you -- are _not your friends._ You can (and should!) be
friendly with them, of course; but you can't have a real, true friendship with
them, because you have power over their lives that they don't have over yours.
Moreover, if you try to just ignore that power differential and relate to your
employees like they're your old dorm buddies, all you'll find is that the
power differential poisons the relationship. They'll constantly be second-
guessing their own reactions to you, out of fear of negative job consequences.
You'll constantly be second-guessing _your_ own reactions to _them_ , out of
fear of appearing to play favorites. And they'll all be second-guessing _each
others '_ reactions to _you,_ out of fear of someone brown-nosing their way
past them on the career ladder.
It's the same reason why it's always a bad idea to date someone who reports to
you -- you can never have the kind of relationship with them you have with
someone outside the hierarchy you sit at the top of. Suspicion and jealousy
and gamesmanship taint it from the moment it begins.
The solution to all these problems is to learn, understand, and internalize
the distinction between _colleagues_ and _friends_ \-- two groups of people
you owe very different things to -- and then act accordingly.
------
bjterry
Google cache since site is down:
[http://webcache.googleusercontent.com/search?q=cache:bfmrmRK...](http://webcache.googleusercontent.com/search?q=cache:bfmrmRKzUdEJ:www.noshortageofwork.com/pages/4063+&cd=1&hl=en&ct=clnk&gl=us)
~~~
bbcbasic
Pastebin for posterity when case Google Cache expires:
[http://pastebin.com/raw.php?i=QtePMR26](http://pastebin.com/raw.php?i=QtePMR26)
------
BrookeTAllen
Hi, this is Brooke, author of the original story.
Wow, other than the grief I'm going to get from my ISP I'm so glad to see all
this and when I get a chance over the next few days I'd like to add more.
Some quickies: I've generalized this approach and talk about it in a Quartz
article: [http://qz.com/88168/how-to-hire-good-people-instead-of-
nice-...](http://qz.com/88168/how-to-hire-good-people-instead-of-nice-people/)
~~~
bovermyer
You might want to look into Cloudflare to help protect your site from the
HN/Digg effect. Free CDN FTW. Also, great story!
------
deedubaya
When you hire for a _person_ , you find that personality traits are much more
important than what an applicant has done in the past, including passion,
drive, etc.
When you hire to fill a position, all this goes out the window the applicant
goes into the hiring lottery pool to maybe get an interview, and then the
traditional "You could totally goog this IRL, but I'm going to hire you based
off your memory" type of hiring.
~~~
bbcbasic
I find that > 90% of interviews to be the latter, unfortunately. The ones
where I got the job were the former! I am stronger at concepts than memory.
~~~
dccoolgai
The worst is when you have to go through one of those interviews with some
smug hoser across from you whose face is contorted into a rictus grin because
you couldn't recall, immediately from memory, some obscure Junior Year
Computer Science thing. It's just amazing how bad the hiring situation is - It
makes me a lot less likely to look around because I just don't want to go
through that.
~~~
MichaelGG
Yet the number of interviewees with a CS degree that can't even _explain_ a
basic algorithm, like traversing linked lists or binary search, is staggering.
~~~
RandallBrown
It's amazing how the brain can totally blank in stressful situations.
~~~
MichaelGG
Eh I doubt that explains it. In my experience, the response is shock. Not "oh
hmm well, lemme think". It's " I've never written that code since school!
That's a terrible thing to ask! Why would I ever write that? "
Also, for trivial algorithms and data structures, mind blanking is a
potentially bad sign. Like, if you cannot explain the idea of garbage
collection (not necessarily implementation details), then I gotta question
your understanding of your environment.
~~~
lukeholder
I am reasonably experienced programmer who has delivered numerous web
applications and websites. I could not explain to you how a linked list or
binary tree worked - although I am sure I could look them up on google and
understand the concepts given 30 minutes.
~~~
dbenhur
"Experienced programmers" who don't understand linked lists and binary trees
without looking them up are strong no hires anywhere I have worked in the last
three decades. Please stop writing software until this isn't a problem.
* edit: please stop asking people to pay you to write software. Keep writing software on your own until such elementary ideas such as linked lists and binary trees are core to your understanding, then apply again.
~~~
vonmoltke
I have yet to encounter a situation in my career that called for a binary
tree. I use general trees and graphs all the time, but never any of the
specialized forms.
Maybe the problems your companies have worked on did. That's fine. Don't go
telling people to "stop asking people to pay you to write software" just
because they don't know how to use or write a binary tree, though.
I agree with you that I wouldn't hire someone who doesn't understand linked
lists, but I still think your statement is too harsh for that situation as
well.
------
bbcbasic
To generalize the point a bit:
I don't think enough companies are doing enough to help the ecosystem.
Like foresters chopping down the Amazon, or fishers taking the last fish from
the ocean, they want to harvest good talent and then stick them in jobs where
they can be a cog in the wheel it is hard to grow. They expect other companies
to have given them the training or perfect relevant experience.
And then we hear complaints there there is a shortage of hackers etc.!
~~~
humanrebar
I completely agree. I would include supporting open source projects as another
way to practice sustainable development. Many kinds of personalities wilt in
corporate environments that could work (for relatively cheap wages) on open
source projects that benefit everyone.
~~~
bbcbasic
I read Michael Church's blog and from reading that I am convinced that we are
our own worst enemy. We spend our spare time writing open source code, which
then businesses can profit from without having to pay any of their own staff.
I think companies should allow staff to spend some time on open source. It
could even benefit the company by having their name associated with it, making
it seem like a cool place to work, and having CV's coming in the 'we're
hiring' page begging for an interview instead of expensive agencies. But there
you go.
~~~
kyllo
I think it's somewhat of a misconception that most OSS is written for free in
professional programmers' spare time. For small projects yes, but corporations
aren't using their code anyway. OSS projects that are prominent enough to
achieve corporate adoption, often have a staff of core maintainers that are
employed by a company that makes money selling support for that OSS software.
Why? Because corporations are risk averse and using OSS without a support
service contract is a risk they won't take. Unless they are a software company
capable of directly supporting the OSS themselves, in which case you also get
devs contributing to OSS projects on company time.
I don't have statistics for this, but I can easily cite a lot of examples.
On the other hand, there are also a lot of contributors that do it for free
but they are not doing it purely out of the goodness of their own heart
either. A lot of them are doing it either because they are heavy users of the
project and/or to practice and build up their portfolio (read: Github profile)
to help them get a job.
~~~
kbart
Not always. TrueCrypt and OpenSSL comes to mind first. Sure, OpenSSL is more
supported now, but it happened only after Heartbleed panic, when everyone
realised how dependant they are on few overworked and underpaid programmers.
Except several well known OSS projects, most others get only peanut money from
donations.
~~~
kyllo
These are sort of the exception that proves the rule, though. Corporations
don't want to rely on poorly supported OSS projects, they prefer to pay for
support so they can hold someone accountable for fixing it when it breaks.
OpenSSL was a bit of a blind spot in this regard. I think corporations just
didn't realize they were depending on it and/or how much of a risk factor it
was, they learned that the hard way.
------
midnightclubbed
So unless I'm reading the cached text wrongly 38 people read the given manual
and answered programming questions based on it. They then met informally. Lets
say they burnt a day on this.
27 of those people then suggested being taught how to program in APL (after
building a classroom). I'm assuming anyone who didnt want to attend got cut. 3
additional days spent.
They were then given 3 weeks to solve some difficult problems. Estimating they
spent 4 days solving those problems.
They then re-met and were interviewed. Another day spent.
So to get to the end a candidate had to spend best part of two work weeks
doing nothing but learning and programming an obscure language. No time for
interviewing elsewhere, earning a wage, or attending college classes.
I would really hope he cared about the majority of the candidates who spent so
much of their own time and money to be rejected with nothing to show for it.
Most companies would have interviewed a couple of times, given a few hours of
programming/aptitude testing and made a decision as to whether to hire the
person (and teach them the job while paying them a fair wage).
Feel free to vote down if I'm getting this all wrong or an being overly
cynical.
~~~
pcthrowaway
I'd like to offer an alternative perspective. The author was both willing to
hire people with no experience, and provided free training to candidates. I
realize that APL isn't a skill in incredibly high demand, but I think the
author may have helped these candidates out in the long term. The ones with
the most aptitude for programming were able to discover that aptitude (and "a
number" of them were hired because of their investment), and the less apt
candidates got a little bit of training and possibly an indication that if
they are interested in programming they would have to accept putting in a bit
more effort than the more apt candidates.
~~~
logfromblammo
Don't confuse training with education.
Free job training is not equivalent to free education. The latter provides
skills and knowledge for the future benefit of the student. That determination
of future benefit is often made by the student. The former also provides
skills and knowledge, but it is for the future benefit of the employer, and
employer-directed. That represents a foregone opportunity. Any trainee could
have spent the same time acquiring free education, traded it working in a job
that does not require that marginal additional skill, or even wasted that time
on leisure activity.
Trainees should always be paid. In this case, they were paid with in-kind
services upon conclusion of the training program. To do less might have earned
the author a reputation for unethical behavior.
Many companies seeking to hire within the software industry do not recognize
the opportunity costs imposed by their hiring procedures. If you require
candidates to waste an entire day or more on your interview process, yes, you
do owe them something for their time. It need not be settled in cash, but if
not, honest feedback on the results of the interview is the bare minimum
acceptable payment. The interviewees are expecting their lost time to be an
investment, not just a gamble.
------
S4M
This hiring process is great, but requires lots of time, for the applicants
and especially for the hiring manager - I suspect the author was targeting
unemployed people, so they would have time for this long application (he put
his job advert on the New York Times). To be honest, that is what surprised me
the most in this article: that someone who runs a statistical arbitrage desk
has the time for all of this.
I wonder if companies could collaborate to create this hiring process. It
would save hiring manager's time, applicants' time since one application will
count for different jobs, and then a system could be set for candidates to
rank their employees, then the candidate who performs the best get his first
wish, the second candidate gets is first wish if there is still room,
otherwise he gets his second wish, and so on - a similar system is being used
in France for students to chose in which universities they want to go after
competitive exam entrance, basically lots of universities pool exams together.
On one hand it would scale hiring process, on the other hand it's not flexible
and offers have to be transparent (it's currently not the case but maybe that
would be a good thing), and it would hurt the pride of companies who are
ranked in the last position.
In the case of the article, I am sure someone who is able to solve in a
language he recently learn the non trivial software that are mentioned will be
able to land a job at some point. It was written in 2004, maybe Github,
Stackoverflow and Open Source in general are now contributing to that
selection.
------
ChuckMcM
Money quote : _" I started No Shortage of Work to encourage my unemployed
friends to re-frame their status not as a disaster but as an opportunity to
explore new vistas."_
This is something which people often forget, is that learning needs to happen
life long, it isn't a 'did college, check that box.' kind of thing, its about
always learning. Its the first thing I check for when I look at people to
hire.
------
BrookeTAllen
Hey, other then the grief I'm going to get from my ISP this is great that
you're interested.
While we figure out how to get my site working again, I wrote this in quartz:
[http://qz.com/88168/how-to-hire-good-people-instead-of-
nice-...](http://qz.com/88168/how-to-hire-good-people-instead-of-nice-people/)
and this for Science Magazine:
[http://sciencecareers.sciencemag.org/career_magazine/previou...](http://sciencecareers.sciencemag.org/career_magazine/previous_issues/articles/2007_11_16/caredit.a0700163)
And there is this Slideshare: [http://www.slideshare.net/BrookeAllen1/brooke-
allen-has-a-be...](http://www.slideshare.net/BrookeAllen1/brooke-allen-has-a-
better-way-of-hiring)
------
sunstone
How bad can it get? Several years ago I had a Russian team lead at a software
company who ate code for breakfast (clearly the top guy amongst over 100
coders) and had excellent leadership qualities.
Later, when the financial crisis hit he was out of work and I found out that
he was really bad at interviews. Ever since I've wondered if I was hiring
would I be able the spot the diamond in the rough where evidently, very few
companies/people can. I'm still not sure.
------
fecak
I sometimes consult to clients on improving their hiring process. Candidate
experience is now a topic that at least some companies consider.
This isn't your typical candidate experience - applying for a vague job ad,
being asked to answer 6 puzzle questions, invite to an open house, two days of
free training and then left alone for three weeks, followed by a vote by the
tribe to see who will get the job.
It's definitely a plus that many of the students were hired elsewhere, but
this is likely a method that would only appeal to the unemployed. I hear quite
a bit of negative feelings towards companies that ask for extensive amounts of
time commitment during the hiring process, and this is probably the highest
level I remember.
If most companies asked candidates to go through this process, I expect they
would want (and feel entitled to) some explanation at the end of the process.
~~~
courtf
Good points here. Some of those who left the process in the beginning may have
simply had better things to spend the next month on, not because they were
inferior candidates. I like the tone of the article in general, but it does
smack of a certain entitlement on the employer's part whereby they feel
justified in extracting many thousands of dollars of free work from unemployed
job seekers. Despite the admirable intentions, the caveat that some of those
who didn't receive a job immediately were later hired elsewhere is only meager
consolation, as I'm sure there were significant contributors who were not
proportionally compensated.
~~~
UberMouse
>extracting many thousands of dollars of free work from unemployed job seekers
I didn't get the impression that they provided any value to the person hiring
them. To me it just seems like they got some interesting, hopefully fun
training in APL over a couple weeks. If I was unemployed and had the spare
time (Like I was a couple months ago) that sounds like something I would have
loved to do.
------
Yhippa
In the US are there legal reasons why employers generally are tight-lipped
about why a candidate didn't get hired?
~~~
sosuke
I've always thought so, and I figure it is a case of our sue-happy culture and
a cover your ass tactic "anything you say can and will be used against you"
kind of fear. I'd love to have reached out to some applicants in the past to
offer help, but what if they don't want any?
~~~
tacostakohashi
It would be nice if, at the start of the application process, companies could
ask you if you would like to agree not to sue them in exchange for open,
honest feedback, e.g. notes from your interviewers.
Sometimes its pretty clear if you are not a good match, but sometimes its
really not, and it seems like it would be best for both parties if certain
kind of feedback could be provided, e.g. you were close, please consider
applying in a year or two with some more experience, or we have decided not to
hire anybody due to a later hiring freeze, but otherwise we would hire you -
or, you are a unlikely to ever work in this industry, don't waste anybody's
time with further applications (maybe some suggestions for better fits).
In general, more information leads to more efficient markets benefits all
participants.
~~~
sgustard
I believe one of your legal rights is you can't be compelled to sign away your
legal rights in exchange for something like a chance at employment.
~~~
tacostakohashi
The idea would be that its optional, and the company would still treat
candidates choosing either optional equally during the hiring process - it
would not be a condition of applying.
So, you aren't signing away your legal rights in exchange for a chance at the
job, you get that either way. You are agreeing not to exercise some legal
rights in exchange for feedback, not in exchange for your application to be
considered.
~~~
edsrzf
If you're agreeing not to sue, then the company can use any criteria they like
to hire or not hire you and there are zero consequences.
Imagine you check the box, you don't get the job, and your feedback turns out
to be "You're a man and we don't like to hire men." You have no recourse
because you agreed not to sue.
You can argue that that's obviously illegal hiring criteria and you should be
able to sue anyway, but then you're back to square one.
------
nostromo
I have mixed feelings about this.
It's easy to see what's to love: an open, honest, and collaborative hiring
process with a boss willing to train employees. Awesome!
But he also got about 30 people to spend four weeks building trading software
for him. Collectively that's over two years of uncompensated work, the results
of which the hiring manager may use for free. And from the perspective of the
applicant, how many applications could they complete in a year if all were so
time intensive? 12? 24? I suspect many top applicants would avoid this process
entirely.
~~~
scotch_drinker
From a worst case cynical viewpoint, he got free labor and those people got
free training. It wasn't like he chained them to a desk and then made them get
jobs in PHP. Best case, it was a mutually beneficial relationship entered into
rationally and with eyes wide open. Top applicants might avoid it but people
trying to break in and show what they can do might jump at the chance.
------
jlukanta
Google Cache mirror:
[http://webcache.googleusercontent.com/search?q=cache:1tQlU00...](http://webcache.googleusercontent.com/search?q=cache:1tQlU00Ks7MJ:brookeallen.com/pages/archives/1234+&cd=1&hl=en&ct=clnk&gl=ca)
------
jdudek
This is quite similar to how we hire Ruby on Rails developers. We organise
two-weeks long Bootcamp where we train people in Rails. At the end we offer
some of them to join us as junior developers, with further training during
next year. Those who are not hired still win—they receive two weeks of
training which helps them find jobs elsewhere. We’ve had some fantastic hires
this way over the past two years.
This article made my think that maybe we can do better and provide more
assistance to those we do not hire after Bootcamp.
More details about our Bootcamps are available at
[http://pilot.co/bootcamp](http://pilot.co/bootcamp).
------
fogleman
So, here is my answer to the question, "What do we owe the people who we do not hire?"
- Information on where they stand.
- An explanation of what they are doing wrong.
- Help improving.
Things you will never get from companies like Google.
------
freework
The best example I've seen for putting together a team comes from my high
school football team. Instead of tryouts, they let anyone play who wants to
play. The best players excel from day one, but the crappy players quit after a
few days. The coach never says to a player "we've decided you aren't good
enough, so you're off the team". It was each players decision that they came
to themselves to leave the team.
The guy in the article pretty takes the same approach. I've always felt the
best way to interview engineers is to go over installing the company's
development environment on their machine. In other words, there is no
evaluation, just expectation of results.
------
seagreen
"So, here is my answer to the question, “What do we owe the people who we do
not hire?”
1. Information on where they stand.
2. An explanation of what they are doing wrong.
3. Help improving."
Nope! You don't owe them those things. Good for the author that they tried it
and it worked out, but it's not a general rule.
Everything works smoother in lots of different parts of life if all parties
understand the concept of a Clean No. Not "You can say No but then you still
owe me such and such". Just "No." Anything beyond that is a gift.
~~~
computerjunkie
Lets talk about a simple example. You apply for a visa to X country for a
special occasion (eg; brothers wedding, graduation ceremony et.al). Two weeks
later, you get a response saying "No", just no.
Will you be satisfied that you never got any feedback to why it was refused,
what you did wrong and what to do to fix it?
Feedback, be it good or bad is crucial. I, myself appreciate this feedback,
especially in this scenario the author is talking about. How am I supposed to
improve my self when I don't even know what I am doing wrong?
~~~
seagreen
Feedback is extremely important. So important, in fact, that you shouldn't
rely on _deeply_ compromised sources for it.
People who have just rejected you will never be reliable sources for feedback
(on average). That's what friends, confidants, and inside sources are for.
------
vonnik
FutureAdvisor's in-house recruiter here.
I recently ran a hiring event in San Francisco with Brooke called Staffup
Weekend. Brooke is one of the smartest, hardest-working and most generous
people I know. I read the post linked to above last fall, and worked with him
to bring jobseekers together to work on meaningful projects. The event was
called Staffup Weekend, and it was held in the Chron building on Mission and
5th.
Our hypothesis was: The only thing that correlates with performance is
performance. Everything else -- degrees, pedigrees, buzzwords, interview
skills -- are a waste of time. About 20 people worked through the weekend to
create various apps. They made wonderful things: one was a Chrome extension
that gives you the emails of the founders of the company web pages you visit.
Another was a LinkedIn 2.0 for people who wanted to feature their work and
themselves. We made 8 interview offers and one hire from the weekend, and I
think everyone involved came away feeling like it was worth it. Write me if
you're curious to learn more: [email protected]
------
skazka16
I interviewed an engineer today. Probably a lot of companies would not hire
him. He was not that great. I said "Yes" because I noticed a passion and a
huge desire to learn and grow. We'll see if that was a mistake or not.
------
ErikRogneby
I attended a bootcamp at ArsDigita on building database backed web
applications back in 1999. I don't recall now if it was two weeks or three,
but the things I learned in that short time have been useful in almost every
job I've had since. Just knowing my way around Oracle an PL/SQL landed me a
position at a telecom. The bootcamp was free, and at the end of the bootcamp
after a code review I was offered an interview. I declined because I didn't
want to live in Boston. I realize that Philips motives weren't entirely
altruistic but I am sincerely thankful that he took this approach to staffing
up.
------
edem
Fatal error: Out of memory (allocated 9961472) (tried to allocate 19456 bytes) in /home/quest15/public_html/brookeallen.com/pages/wp-includes/taxonomy.php on line 959
------
spydum
The real solution here is not to interview people, but to discover people
OUTSIDE of a hiring scenario, and recruit them after you've determined they
would be a great fit (inverting the game). It's just unfortunate that it is
much more effort to invest as the employer, but it is essentially the best way
for everybody involved.
------
alishan-l
As a job seeker having recently completed a web dev bootcamp (with no prior
experience), how might I go about getting my first tech job? Or, taking a step
back, my first interview? I find it frustrating that entry-level positions
seek people with years of experience.
~~~
joshdotsmith
One thing to keep in mind is that "entry-level" means the most junior position
with that company, not "entry-level" into the workforce at large. I found this
equally frustrating in non-technical jobs after I graduated college (with a
liberal arts degree). It's a rather encumbered naming convention.
------
grimmfang
Google cache of this page:
[http://webcache.googleusercontent.com/search?q=cache:1tQlU00...](http://webcache.googleusercontent.com/search?q=cache:1tQlU00Ks7MJ:brookeallen.com/pages/archives/1234+&cd=1&hl=en&ct=clnk&gl=us)
------
normloman
This sounds like the job search from hell. Let's break down this trainwreck:
1\. The guy posts a vauge help-wanted ad that implies no experience is
required. Then he's surprised that 300 people applied and none had relevant
experience.
2\. He asks applicants to read a 500 page manual, then solve some programming
puzzles. With no pay. As if the applicants have nothing better to do.
In the rest of the story, the guy does a nice thing for the remaining
applicants. But why does he ask candidates to jump through so many hoops for
this job, especially when, as he states in the ad, experience is not required.
Not every unemployed person has the time to read a manual, waste time solving
puzzles, or attending a class with no guarantee of employment. Some of them
_really need jobs_. Some of them have bills to pay. Some of them have other
opportunities, and can't afford to put their life on hold while you make up
your mind.
------
anon4
Or "How my life improved once I started making friends"
------
soheil
"Resource Limit Is Reached"
this is how
------
sonabinu
brilliant!
| {
"pile_set_name": "HackerNews"
} |
'Safety issues' prompt Apple charger trade-in programme - tomorgan
http://www.bbc.co.uk/news/technology-23585898
======
tomorgan
+1 to Apple here - they don't have to do this.
But maybe it's the cheapest way to: a)deal with fake chargers b)turn a -ve
story into a +ve c) still sell chargers at a profit.
| {
"pile_set_name": "HackerNews"
} |
Decorators in Go using embedded structs - fabianlindfors
https://fabianlindfors.se/blog/decorators-in-go-using-embedded-structs/
======
AYBABTME
Embedding like this will only lead to pain long term. It's preferable to
implement the interface you want to fulfil directly (by having actual method
definitions), despite the extra ceremony. Inheritance with embedding is a
false friend in Go. Stick to composition.
If you want to delegate a call to a "subtype", simply invoke the method on the
subtype by writing it out in long form. It doesn't make you feel as
intelligent but it's way more robust and won't come back to bite you down the
line.
~~~
weberc2
> Inheritance with embedding is a false friend in Go. Stick to composition.
Note that this applies to every language with inheritance. Composition is
_always_ better.
~~~
AYBABTME
I don't disagree. I just think it's particularly bad in Go.
~~~
pm90
Do you say this specifically because of struct embedding?
------
avita1
I find the comparison to java a bit unfair, because this pattern is totally
possible but has been largely deemed a bad pattern. The analog to the pattern
in java is to extend from a non-final class. So in this case "class
HTTPClient" and "class CachedHTTPClient".
There are lots of drawbacks to doing it that way, the worst of which is that
you need to remember to override the method in CachedHTTPClient everytime you
add a method to HTTPClient, and the compiler gives you no hints about it.
~~~
jerf
It's important to deeply understand why patterns are deemed bad in one
language, so you can see if it applies to another language [1]. In the case of
Go, we generally try to keep interfaces small. In many real-world cases of
decoration in Go, probably the vast, vast majority, the interface only has one
method, so there isn't any way to forget to override the other methods.
While there's no particular exact language feature I can point at to say why
this happens, in general, Go interfaces are more fluid since they don't have
to be declared up front, and end up being kept simpler than Java classes and
interfaces, so the concerns about failing to override other methods are
greatly, greatly reduced. They are not technically eliminated, but they're
pushed way, way down my list of priorities.
[1]: This is not special pleading for Go, it goes well beyond that. A good
design in Java is a bad design in Python, a good design in Python is a bad
design in Java, etc. If you had two languages where the exact same patterns
were appropriate in the exact same way, I'd question whether you actually had
two languages.
~~~
jayd16
This doesn't protect you in the slightest. The failure case is clear and
likely for something like an CachedHttpClient where every call should be
cached. You're talking hypothetically but here's a simple common failure case.
~~~
jerf
How do you fail to implement the second method override on a single-method
interface?
Bear in mind that when using the interface, the interface is all there is. It
essentially erases the other methods from consideration. That's why an
interface value in Go is a distinct type; it isn't just "a thing that can
happen to hold all these various concrete values", it is a distinct thing with
its own method set. So discussion underlying structs and their method sets is
a category error. (This is a bit subtle, but important to understand what is
actually going on in Go, or any other language with a similar setup.)
I'm not talking hypothetically. I'm talking about what happens in _real_ Go
code. Discussing what could happen if people wrote interfaces in a way other
than they actually do is what is hypothetical. This is the sort of thing that
matters when deciding whether or not a particular pattern is useful in a
language. It's rarely entirely down to pure syntax concerns or some sort of
Platonic software engineering consideration. In fact, even within the same
language you can encounter situations where a pattern makes sense in one
_framework_ but is a bad idea in another _framework_ ; Javascript is full of
such things. (Whether that's for good or bad reasons is a separate
consideration; the fact is that it is full of them.)
~~~
jayd16
>How do you fail to implement the second method override on a single-method
interface?
Well in the example given, there is an interface Client with two methods. If a
maintainer controls the Client interface and the HTTPClient implementation,
the case can occur where that maintainer updates Client and HttpeClient.
Suddenly, CachedHTTPClient in the downstream project has an unchached method
and as far as my limited Go knowledge goes, no compiler error.
>I'm talking about what happens in real Go code
The case appears in the blog post. Would you say the blog is not idiomatic Go?
~~~
jerf
"Would you say the blog is not idiomatic Go?"
Yes, it's a contrived example to make the point in the blog. Blog samples have
to be taken that way. The vast majority of the time real code decorates in Go,
it's with either A: an interface of 1 method or B: something sufficiently
local in concern that this sort of thing isn't a concern, beyond it just being
a bug (a compiler forcing you to specify an override won't save you from just
sticking the minimal stub in). Part of why this can be a problem in Java is
you tend to get a certain sprawl to your class hierarchy that doesn't occur in
Go. Or most other languages, used well. Java's got some unique weaknesses in
this area that do not generally translate.
~~~
jayd16
I personally think it has more to do with the coders than the code. Seeing as
it's trivial to do it wrong in Go (see blog) I have to assume IBM websphere Go
would be a similar nightmarish hellscape as it is in Java.
------
inlined
This is a bad practice in Go for any interface type. Interfaces which are
wrapped will fail all type assertions against their original type and fail to
assert into additional interfaces that the original also implemented.
For example, imagine you have an io.Reader. It may actually implement
io.ReaderTo which is used in some cases to implement alloc-free copying. If
you wrap it into a new struct, e.g. ioutil.NopCloser you delegate the main
interface but not the bonus interfaces. You can no longer cast to the type of
the original reader interface either (concrete type comparison is more
important with errors, which had a custom fix in Go just for this)
~~~
fabianlindfors
If we have an io.Reader which implements io.ReaderTo then it has a certain set
of exported functions. If this is embedded in ioutil.NopCloser then all those
exported functions will be available on ioutil.NopCloser. Wouldn't structural
typing then ensure that ioutil.NopCloser implements io.ReaderTo as well as
io.Reader?
Sorry if I'm misunderstanding!
~~~
omegabravo
[https://play.golang.org/p/V3eWfbDGhXF](https://play.golang.org/p/V3eWfbDGhXF)
In this example, by wrapping an interface in another interface, you lose the
ability to cast back down to an interface that the original type fulfilled.
~~~
fabianlindfors
Thanks for putting that together, I see your point know. Thought you were
talking about embedding when you said "wrap" before.
Considering that this is not related to embedding specifically, would you say
that decorators in general are bad practice in Go?
------
avalanche123
This pattern is called Composition
([https://en.wikipedia.org/wiki/Composition_over_inheritance](https://en.wikipedia.org/wiki/Composition_over_inheritance)).
What makes it much more practical in Go than in say Java is struct embedding
and implicit interface implementations
~~~
jayd16
Exporting structs doesn't seem like composition to me. It seems much more like
multiple inheritance.
~~~
weberc2
It is exactly composition; the compiler just generates the methods to
automatically delegate to the anonymous elements. It's just syntax sugar that
probably creates more confusion than it alleviates. It's not inheritance of
any kind because the outer struct cannot be passed into a function that takes
the inner element type (e.g., if you have `type B int` and `type A struct {B}`
and `func foo(B) {}`, you can't pass an instance of `A` into
`foo()`--`foo(A{B: 0})` is a compiler error.
As it is just composition, it is strictly better than inheritance, but still
probably unnecessarily confusing versus just writing out the delegation
methods yourself.
~~~
jayd16
>It's not inheritance of any kind because the outer struct cannot be passed
into a function that takes the inner element type
My mistake. I was mislead by the blog post.
From the article:
> The new type would be interchangeable with the existing client which would
> minimize the need for changes to existing code.
So with go exported structs it is not fair to say they can be used
interchangeably if at any point that instance is used as a parameter, field,
or variable that defines the type?
In the examples given in the article, the thing that is used as parameters is
the interface Client not the concrete type HTTPClient. Would that not allow
CachedHTTPClient to passed around as if it was a Client and would that not
show the same issues as inheritance?
~~~
weberc2
Both types implement the `Client` interface. So either type can be passed into
a function that accepts the `Client` interface, but a `CachedHTTPClient`
_cannot_ be passed into a function that accepts an `HTTPClient` (you would
have to pass the `CachedHTTPClient.HTTPClient`) and of course not vice versa
either. You can do the same thing in Java (forgive my syntax):
public interface Client {
ArrayList<String> getUsers();
void createUser(String name);
}
public class HTTPClient implements Client {
public ArrayList<String> getUsers() { /* ... */ }
public void createUser(String name) { /* ... */ }
}
public class CachedHTTPClient implements Client {
private HTTPClient httpClient;
public ArrayList<String> getUsers() { /* ... */ }
// In Go via "struct embedding", this method would be generated
// automatically; in Java, we have to write it out. NBD.
public void createUser(String name) { this.httpClient.createUser(name); }
}
~~~
jayd16
Makes sense. I guess I just don't see how exported types save you from any of
the pitfalls of inheritance. In my mind composition is the use of existing
types _without_ being forced into a type contract.
~~~
weberc2
Mind you, I don’t advocate for struct embedding, but it doesn’t force you into
a type contract. The outer struct retains its type—it is not a subtype of the
nested type so it can’t be used in places that take the inner type.
Literally all it does is automatically create methods on the outer struct that
delegate to the anonymous member.
Unlike inheritance, there is no fragile base class problem and methods on the
inner anonymous member can’t dispatch to methods on the outer struct. Also,
the “parent” member is just another field in your struct. You can modify it or
replace it at runtime, unlike the parent in OOP languages.
------
pram
A small critique on your examples: you never actually show using the Client
interface anywhere. Might be useful to someone new to see how you'd switch out
HTTPClient for CachedHTTPClient using it.
~~~
fabianlindfors
Good point, thank you!
------
ljm
There’s probably more but the singular best use-case I’ve found for embedding
a struct is when you want a mutex.
That is elegant.
This example looks nice, but I think the naming of the structure and
interfaces makes it hard to follow and a cache doesn’t necessarily benefit
from it. In fact, it’s worse if your cache isn’t in-memory, and you’re not
sharing an instance or a connection pool. If you are, this is just indirection
and you can live with `Cache.get` just as well.
~~~
sethammons
I'd recommend only embedding a mutex on private structs - you likely don't
want to expose Lock and Unlock.
------
yepthatsreality
I think this is also a good primer into golang inheritance and composition,
which are major concepts in successful golang programming.
~~~
inlined
golang doesn’t believe inheritance is necessary. Be careful trying to put a
square peg in a round hole.
~~~
weberc2
golang is right :) Seriously though, Go doesn't have inheritance and I don't
miss it. The only reason I need it in Java, etc is because so many libraries
expect/require you to subclass.
| {
"pile_set_name": "HackerNews"
} |
Timber: A library for realtime pitch detection in web apps - abstractbill
http://abstractnonsense.com/timber
======
jwecker
Wow, excellent. That's a ton of processing squeezed down to something very
fast and light. I'm excited to see what kind of signal processing can come out
of this.
| {
"pile_set_name": "HackerNews"
} |
A factory that supplies Apple and Nokia used the toxic solvent n-hexane - Kudgeon
http://www.globalpost.com/dispatch/china-and-its-neighbors/100312/apple-news-iPhone-asia-illness
======
illumin8
After reading the article, there seemed to be one factory manager that started
using this solvent because it dries faster than alcohol, allowing him to shave
a few seconds off the production time of each flat screen.
They said this manager was fired, and based on the number of employees
spending sick days in the hospital, I'm sure the company ended up losing a lot
of money on their medical bills.
This is hardly newsworthy. It happens all the time in China. Someone unethical
wants to skim a little money by using cheaper chemicals, or wants to make a
few more cents by producing faster using an unsafe process.
You can't blame Apple or Nokia. They likely dictated exactly what solvents
were to be used, but the supplier decided they can hire fewer workers if they
use the faster drying solvent, so they decided to cut corners.
~~~
wdewind
For the sake of playing devil's advocate:
These chemicals are having an effect on the Chinese economy, and thus the
world economy (globalized economic impact), as well as in some cases the
environment. That kind of changes whose responsibility it is, because it
really does affect all of us (this is a localized case, but there are many
American manufacturers who manufacture items in China with methods that
severely harm the environment in and out of China). Apple really should
maintain more control over manufacturing processes. As a major player in both
the US and the entire world, and a representative of the US economically (this
is important because we constantly ask 3rd world countries to cut emissions
and regulate things like this), they have a responsibility to make sure they
don't do things like this in all areas of product creation (just because its
offshore and outsourced doesn't mean they have 0 responsibility) when the cost
of ensuring it to them would be essentially unnoticeable.
If it would be extremely costly to do this kind of regulation (since the
Chinese obviously wont) on Apple's part, it would be reasonable to discount
their responsibility, but it really wouldn't be that expensive if they wanted
to. It's a bit naive to assume that Apple isn't knowingly turning a blind eye
to manufacturing conditions. Apple obviously knows things like this are prone
to happen when you outsource manufacturing in 3rd world countries, so maybe we
should be asking them to do a better job of regulating who they do business
with considering the range of impact they actually have...
------
protomyth
With journalism like this, what reason would any company like Apple publish
audits when it will be distorted for link bait. I was so hoping that with the
advent of the web we would get decent investigative reporting, but the
sensational headline has been replaced with SEO.
~~~
mbreese
Agreed. This isn't a problem for just Apple and Nokia, it is a problem for the
entire industry. In fact, I'd argue that this should be _less_ of a problem
for Apple, because their products aren't necessarily as pricing sensitive as
the Lenovo, Dell, and HPs of the world.
I think that there is a reason why other companies haven't done or published
an audit like Apple... they don't want to know the results. If they knew the
results, then they'd be obligated to do something about it.
------
justin_hancock
Whilst there maybe some nasty sensationalism going on here, that does not
entirely exonerate Apple/Nokia. They put enormous pressures on their suppliers
to deliver more goods in less time. The inevitable consequence is that the
supplier pressures the production line to produce more and nasty shocks like
this okay. The fact that this went on for a year or so unchecked means Apple
is not auditing regularly enough. If Apple were running the production process
itself I doubt this would happen, however when it outsources it does. Apple
needs to be a good corporate citizen and also put its money where its mouth
is, if suppliers do this cut them off.
------
Loic
Toxicity of N-Hexane on Wikipedia.
<http://en.wikipedia.org/wiki/Hexane#Toxicity>
Basically, the problem is more the volatility than anything else, so it may be
bad for the poor Chinese people working "just there" but for the end user in
Europe, this is safe as it will have evaporated long before reaching us.
Call me a cynical, but for one case like that, how many unknown cases?
Especially because in China/India, you contract one company which will sub
contract to an array of smaller companies with often very bad working
conditions.
------
Kudgeon
It certainly sensationalizes one side more, and I think that companies can't
extensively look over every part of their manufacturing process that they
outsource. However, companies like Apple and Nokia need to be a little more
socially responsible and monitor who they do business with . . . obviously
easier said than done.
------
plaes
Well, isn't "everything" around us toxic, when handled inappropriately without
proper equipment and caution?
Take water (dihydrogen monoxide) for an example - you can drown in it. Or pure
ogyxen - extremely flammable.
So it isn't about toxic substances - it is about handling them with care.
~~~
ars
You got downmodded because the first part of what you wrote seemed silly.
But your point about handling them with care is correct. You can use n-hexane,
but only if you handle it properly.
------
idlewords
For context, n-hexane is essentially gasoline.
------
hackermom
I don't like how the author of the article angles the irresponsible actions of
those in charge of the factory, as being the fault of Apple and Nokia. There
is a consistent tone of "Apple/Nokia uses illegal chemical n-hexane in
factories". Simple sensationalism.
------
anApple
And that's the reason why I don't buy apple products. Apple has used many
toxic/nature killing compounds in the past as well.
| {
"pile_set_name": "HackerNews"
} |
Is Groupon’s Bizarre CEO Ruining His IPO? - davj
http://gaw.kr/nAjhLr
======
NYentrepreneur
Read this analysis of Groupon's business, and I think after you do (and
factoring in the company's CEO 2 years ago was a MUSIC STUDENT):
<http://www.privco.com/private-company/groupon-inc> ...and I think you'll see
the answer to your question is: duh.
| {
"pile_set_name": "HackerNews"
} |
Show HN: Simplemap – Plot GPS Points on a Google Map with Python - patrick--
https://github.com/patrick--/simplemap
======
patrick--
This is a small project I threw together to allow for quick visualization of
GPS coordinate points. It's a work in progress, so it still needs some polish.
------
sccxy
I would use Leaflet for this simple map.
Lightweight and fast.
[http://leafletjs.com/](http://leafletjs.com/)
| {
"pile_set_name": "HackerNews"
} |
Show HN: I built a free forms service for static websites - yupitszac
https://www.formking.io
======
nkron
This looks really nice but I was burned by another free form service
([https://news.ycombinator.com/item?id=16466147](https://news.ycombinator.com/item?id=16466147))
that just disappeared without any notice.
I ended up switching to using a Google script which I've been happy with so
far: [https://github.com/dwyl/learn-to-send-email-via-google-
scrip...](https://github.com/dwyl/learn-to-send-email-via-google-script-html-
no-server)
~~~
135792468
Ditto. [https://www.palabra.io/forms/](https://www.palabra.io/forms/) was
around here a few weeks ago and I just started using it when it went
missing/broken.
I’ll try your google solution, thanks
------
aioprisan
Would you be willing to open source this? That way it can stay free forever
(at least basic functionality) and you'll likely increase the adoption by
other folks.
------
agustif
I've been recently looking for form solutions
Free [https://www.staticforms.xyz/](https://www.staticforms.xyz/)
[https://formsubmit.co/](https://formsubmit.co/)
Paid [https://formbucket.com/](https://formbucket.com/)
[https://formspree.io/](https://formspree.io/)
You can also check out Netlify Forms
~~~
notwhereyouare
I'm currently using formsubmit and I'm pretty happy so far. As far as I know,
I haven't had any issues getting responses
~~~
agustif
I had to switch from it last minute, because one of my forms wouldn't
activate, actually, I did get the Form Activated to appear, and some emails
passed, but then It was still deactivated, and found myself in an endless
loop. Idk, but I had to go with a paid option so my boss would be reassured it
would work on monday.
Anyway a few more I found when I had to switch last time, I went with
usebasin.
[https://liveformhq.com/](https://liveformhq.com/)
[https://www.formbackend.com/](https://www.formbackend.com/)
[https://www.netlify.com/products/forms/](https://www.netlify.com/products/forms/)
[https://formbucket.com/](https://formbucket.com/)
[https://www.formking.io/](https://www.formking.io/)
[https://formspree.io/](https://formspree.io/)
[https://www.staticforms.xyz/](https://www.staticforms.xyz/)
[https://formcarry.com/](https://formcarry.com/)
[https://formkeep.com/](https://formkeep.com/)
------
Zaheer
PSA: You can do the same thing with Google Forms + Sheets.
Here's how to post to a Google Form:
[https://stackoverflow.com/questions/18073971/http-post-
to-a-...](https://stackoverflow.com/questions/18073971/http-post-to-a-google-
form)
~~~
yupitszac
Yea absolutely! You can also just build a form backend to handle your data
collection. Or even just use another forms service (there are a ton).
This was just a personal project that I made available in case anyone else had
a need for it :)
------
ibdf
Nothing free lasts forever, but that's how a lot of people gage interest
anyway. Having said that... this is a good solution for small site's contact
form which you wouldn't care much about privacy or if it went away in a couple
of years.
------
st-isidore
Nice job offering something for free. I'm not as skeptical as some here; looks
like you just wanted to build something useful for people and it's not going
to cost too much to provide it. At the very least, it's a great project to
have under your belt, with real customers, etc. Could help landing jobs, for
sure!
I had to figure out how to handle my contact form on my static blog recently,
and I decided to simply write a form handler with Go and deploy it on Google's
Cloud Functions. It's free for now (and probably always will be considering
the fact that I'll probably never receive more than ~10 form submissions per
month anyways). The function takes awhile to spin up cold, but it doesn't
matter too much. I like it because the code is simple and I "own" the service.
Curious to hear what other static site admins have decided to use for their
forms.
~~~
yupitszac
Thanks for the thoughts! It's still a young service, and honestly there are a
ton more users than I expected so early
GO is super interesting, and I like that you wanted total control over your
process. I've never used Google Cloud Functions but that's similar to Azure
Functions or AWS Lambda, yea?
------
kurzawa7
The forceful over emphasizing of "Free. no bullshit" throughout the website is
off putting
~~~
kevincox
Yeah, I'm wondering why it is going to stay in service? Maybe they should
emphasize that they are donation supported (if that is the plan).
------
bgdam
I might be in the market for a forms service, and have been researching them a
bit over the past few weeks. As a potential customer, here is the single
biggest thing that made me instantly say no: free. Even worse it's unlimited
free, not even freemium.
That means either the service will sell my information, or the information of
my customers (if not now, eventually), or that it's going to die shortly. And
I don't want to put in the effort of migrating my sites to your service in
either of those cases.
So my advice to you is to start charging.
~~~
radmin
Yes, please start charging. Aside from the effect it has on perceived
trustworthiness, longevity, etc., giving away your work for free undermines
others' ability to make a living selling theirs.
~~~
Hamuko
> _giving away your work for free undermines others ' ability to make a living
> selling theirs._
That's not his problem.
~~~
digitaltrees
But it is. It’s called a race to the bottom. While it’s a normal price setting
function of free markets that doesn’t mean its rational.
~~~
CM30
So people shouldn't have a blog, since people read that content instead of
paid books, magazines or newspaper articles? Or post videos on YouTube,
because TV and films aren't free? Or work on open source software, since that
might save people the need to buy software from companies that are selling?
Truth of the matter is, an awful lot of things that were previously
commercially viable simply aren't any more because people are happy giving
them away for free or releasing them with ad support. Few people will buy a
web browser or CMS or programming language compiler/interpeter/envrionment,
because free competition has made commercial ones obsolete.
Either way, it's just life. Things that were once expensive services only
available to wealthy became commoditised and affordable for pennies, and new
types of business became viable in their place.
So if you're running a company selling a form service and free competition is
outcompeting you, then you'll have to adapt or die like anyone else. Or find
some value proposition people are willing to pay for in that area (support,
customisations, lots of new features, a glossy design, etc).
------
ixxivvix
I kind of hate the profanity being part of the branding, or anywhere else that
I’m going to use professionally. It’s pretty useless since it’s not actually
describing the service (what exactly does “no bullshit” mean for forms?), and
just detracts it and the team or developer who made it.
~~~
oftenwrong
What if they billed it as "formking awesome"?
~~~
sbruchmann
It doesn't have the same ring to it as "our prices are sofa king low"
------
redis_mlc
Looks like a good MVP, but the .io domain is a non-starter because of the past
registrar/mgmt. problems (ie. entire registrar and DNS being pwned.)
If anybody knows if .io mgmt. is professionally managed now, let me know.
[https://www.theregister.co.uk/2017/07/10/io_hijacking_in_tra...](https://www.theregister.co.uk/2017/07/10/io_hijacking_in_transition_cockup/)
~~~
specialist
Thank you for this. I wouldn't have known to even look. Now I wonder if there
are TLD and registrar auditing and rating surveys.
~~~
redis_mlc
FYI:
\- stick with .com
\- avoid .tv, or any islands/small kingdoms
\- .id is underfunded (lifetime domains, so no renewal fees)
\- research anything else
~~~
MildlySerious
Equally, something seems to be up with .af currently. Both Gandi and Namecheap
can't register those currently (only places I checked) and haven't been able
to for at least a week. No idea how long this has been going on.
------
TomGullen
You’re presumably storing a lot of personal data - perhaps inadvertently. How
are you handling the minefield of data protection?
~~~
hadtodoit
I don't think anyone is using his service, including himself. This page on his
personal website uses a google form.
[https://www.yupitszac.com/life-of-a-
contractor/](https://www.yupitszac.com/life-of-a-contractor/)
~~~
yupitszac
Of the hundreds of forms out there across the static properties that are mine,
and that I work on, it'll take time to convert them all.
As for user counts, one of the benefits of it being a personal project is that
I don't have to share or defend that. It's a service that's there, if you want
it feel free to use it. If not, that's completely okay too
I'll add that form to my list for conversion though, so at least thanks for
that :)
------
staticvar
Cool stuff. If you are interested in doing multipage forms and need something
that already has a form editor UI, check out the open source <tangy-form> and
<tangy-form-editor> web components. Disclaimer, I'm a contributor to those
projects.
~~~
swiley
Or just don’t do multi page forms because those are _very_ unpleasant.
~~~
karagenit
They definitely have their place. For example, if the answer to one question
affects which other questions are relevant it's nice not having to put down
"not applicable" in a bunch of answer boxes.
------
harrisreynolds
A bit more feedback after looking at your site.
First... put a live form on the home page.
Second... include a screenshot of the a live form, not just the backend of
form submissions.
Third, for extra credit... create a simple video of using the tool end to end.
Best of luck!
~~~
yupitszac
Thanks for the feedback! It's still a super young service that I built and
work on in my spare time. I was already working on some blog posts, but the
video idea is perfect!
A live form, of course. People want to see how it works and play with it. I'll
get these put together and up soon! Thanks again for taking a look :)
~~~
apotropaic
Another idea along those lines... I like to play with the form builders before
creating an account. Shows what field types are available and how it works.
Maybe a demo site?
------
AussieCoder
Shameless plug - StaticForms
([https://staticforms.co](https://staticforms.co)).
It's not free because I want it to be sustainable, but also because it does
more than just capture form data and send you an email. You might not need
more than that, but if you do then it's probably even more important that it's
a sustainable business.
------
filvdg
We are running [https://formlets.com](https://formlets.com), wishing them the
best, i can tell one thing from experience, we have a free offering too, 100%
free is not sustainable,you will need payed accounts to get a sustainable
business, within weeks to months (depending on the popularity) the phishing
people will find your service and you will need a full time person to track
them and remove the forms or your reputation will be toast. Its a brutal
market to be in.
------
harrisreynolds
Looks good Zac! I love that you came straight out of the gate with "No BS".
Classic!
I've built a similar service but it also includes a website builder if anyone
here is interested. Check it out at
[https://www.webase.com](https://www.webase.com)
------
padseeker
I think one of the challenging parts of selling a form builder is trying to
figure out where you draw the line of free to paid. Do you limit the number of
submissions? Per month or forever? The number of forms? The number of inputs
per form? Access to the API? Integration?
------
jlelse
I built a self-hosted tool (for myself) that sends form submissions via email:
[https://git.jlel.se/jlelse/MailyGo](https://git.jlel.se/jlelse/MailyGo)
------
agentultra
> Form King is free, but ti doesn't have to be ugly
Spelling mistake there.
Nice looking site!
~~~
yupitszac
Thanks for the heads up :) I've pushed a correction
------
snake117
Thanks for sharing! Do you mind me asking what admin template you used for the
app? I'm searching for a decent admin template right now with a similar color
scheme.
------
victoriasun
This is great and super useful! The admin panels are shockingly well designed
for something that is free. Thank you!
------
eitland
One interesting thing: the landing seems to load pretty much instantly in both
safari mobile and ff mobile :-)
------
rmnclmnt
I'm sorry but no privacy policy and not an open-source/free-software? I find
it hard to believe it is "free" as in free beer...
Shameless plug: if you want a self-hosted AGPL-3 alternative with optional PGP
support, checkout "mailer":
[https://github.com/rclement/mailer](https://github.com/rclement/mailer)
------
martinald
I love how we are back to the world of cgi-bin formmail style services, after
about 20 years.
~~~
simlan
Yep exactly my thoughts.
------
sdan
You can do this with Netlify
~~~
lucasverra
paying after something like 100 submits..the value here is "free"
~~~
nvr219
100 free submits/month. I use this for my tiny side projects. Anything that
needs more I would want to pay for anyway (like everyone else said here)
------
time0ut
Is there a privacy policy? I couldn't find one, but maybe I didn't look in the
right place.
How do you intend to monetize? It is important to make sure your business plan
aligns with my potential use cases.
Small typo: it is misspelled as ti on the landing page.
It looks cool and I'll give it a try, but I need to know more than is
obviously apparent from your site before I can use it for real.
~~~
yupitszac
Thanks for the feedback :)
Privacy policy, yea. I gotta get one of those up. Incredibly important things
like that and terms of use should be sorted right away. This is one of the
things I forget about in my personal projects (like FormKing) that I really
should stop forgetting :)
As for monetization, that's not my goal. One thing I don't think I
communicated well is that this isn't a business. It's a personal project that
I intend to open source shortly. The cost for the service (hosting, domains,
etc) is super low so for right now I'm not looking to monetize.
Form King was literally just something I built for use with my websites that I
had a lot of fun working on. So I made it public
------
CoreSet
As someone who recently added a "fremium" / "free for solo developers" tiers
to their form service this is fascinating.
We give you unlimited forms but gate on submissions, offering more features /
submissions in higher tiers etc.
Reading the blog it doesn't look like there is anything malicious about
selling user data or some "you are the product"-type bait and switch, but with
one dev and no financial incentive I don't see how he keeps this going (No
knock to him, asking unlimited free work is a lot).
Forms seem like sort of a small thing, but you really want them to _work_.
Having a whiff on even a contact form can miss a lead and looks bad. And if
the service breaks, all of a sudden you have to change a bunch of source code
pointing to a defunct service, and hope they have an export function.
(shameless plug for the curious, since some people are suggesting services:
[https://formcake.com](https://formcake.com)
~~~
aroch
Shouldn't your tag line be "The Form Backend Built For Developers", with
"built" not "build". And a little more unsolicited feedback: the
rendering/display of code example under /How It Works/ looks kind of sloppy --
I think it might actually look better when JS is disabled. Similarly, not a
big big fan of the fullwidth Codepen embed.
~~~
CoreSet
Thank you for the feedback!
------
satvikpendem
Reminds me of StaticKit ([https://statickit.com](https://statickit.com)) by
Derrick Reimer who built Drip and co-hosts the Art of Product podcast. There
might be some interesting lessons if you listen to their podcast, many of
Reimer's insights on static site forms are made public through it.
~~~
CoreSet
The funny part about this too if you listen to the podcast is that Derrik
Reimer is ending statickit because he is having trouble monetizing it /
finding product-market fit with static sites.
~~~
satvikpendem
Interesting, I haven't listened to the latest episodes. Netlify already has
forms, as do other vendors, so I don't see too much of a use for StaticKit,
unless you host your site on your own servers rather than a CDN.
| {
"pile_set_name": "HackerNews"
} |
13k datasets, 100 million time series, 600 million facts - coderdude
http://blog.datamarket.com/2011/01/23/13-thousand-data-sets-100-million-time-series-600-million-facts/
======
skorgu
Fun to play with but no free level for the API seems odd. The FAQ is
unhelpful: [http://help.datamarket.com/kb/using-data-from-
datamarketcom-...](http://help.datamarket.com/kb/using-data-from-
datamarketcom-elsewhere/api-basics)
~~~
hjalli
As mentioned in the FAQ, there are 50 free API requests per month for every
registered user. I updated the FAQ answer a little bit, but feel free to
contact if anything remains unclear.
~~~
skorgu
Maybe I'm dense but I don't see any API documentation on how to use it.
| {
"pile_set_name": "HackerNews"
} |
Lego is so popular, it can’t keep up with demand - davidbarker
http://www.theverge.com/2016/9/7/12829974/lego-sales-2016-growth-demand-factory-strain
======
qq66
Companies that quickly expand to meet sudden demand find themselves over
capitalized when the demand inevitably drops, and often bankrupt soon
afterwards.
Lego has always been managed for the long term and I assume they will grow
production capacity only to the extent that they believe the demand growth is
structural and not cyclical.
~~~
eternauta3k
They could raise prices if they didn't mind the negative PR.
~~~
carsongross
But why?
The glory of privately held companies is that they can say "Enough. There are
things more important to me than another dollar."
And when I say "they" I literally mean a small group of humans, able to
project non-monetary desire onto corporate behavior. The abstraction of public
ownership does away with this, leaving only "more".
~~~
bitwize
And that's the difference between conservative but revolutionary, in it for
the long haul private Nintendo and trend-chasing, Super Mario Run, "we have
shareholders to appease, let's throw anything at the wall and see what sticks
but in the meantime here are a few tentpole franchise remakes/rehashes" public
Nintendo.
------
behnamoh
This post reminds me: History repeats itself.
Once upon a time, we moved from 16-bit graphics to 32-bit and more. Everything
seemed so lively and real. Windows XP icons suddenly became so lovely.
Now, it looks like we're bored with these great graphics again, and want to go
back to the 80s and 90s. So we build games and animations that resemble that
16-bit graphics.
Odd thing is, now we watch 16-bit, pixelified faces on 32-bit Full HD screens.
A few years later, all this hype about "flat design" will subside, and we'll
miss XP icons again.
And so it goes on and on...
~~~
vollmond
Just like fashion, just like music, just like everything involving aesthetics,
no? It's cyclic.
~~~
behnamoh
Yeah, exactly like fashion.
------
petilon
Grown-ups can play with Lego too! Here's a GBC (Great Ball Contraption); looks
like lots of fun:
[https://www.youtube.com/watch?v=sUtS52lqL5w](https://www.youtube.com/watch?v=sUtS52lqL5w)
~~~
todd8
Thanks for the link. I've been to Lego Land in San Diego and seen Lego
exhibits before, but I've never seen anything like the GBC!
------
AstroJetson
It does, but for some of us Legomaniacs it explains why some things are hard
to find.
But you need to wonder, do people throw Lego away? Hopefully they get handed
down from generation to generation.
~~~
jpindar
Apparently there's quite a market for used Lego.
[http://embedded.fm/episodes/157](http://embedded.fm/episodes/157)
~~~
douche
[http://www.bricklink.com/catalog.asp](http://www.bricklink.com/catalog.asp)
You can find almost anything.
------
ddebernardy
Pretty cool. And far cry from the hole they were into a few years ago:
[http://knowledge.wharton.upenn.edu/article/innovation-
almost...](http://knowledge.wharton.upenn.edu/article/innovation-almost-
bankrupted-lego-until-it-rebuilt-with-a-better-blueprint/)
------
donbronson
Seems to me the biggest takeaway from the article was that it was Lego's
partnerships that saved the company. Without those deals with Star Wars (for
example), the company would have not needed to meet demands in the first
place. This seems like a big lesson to learn from.
------
JoshGlazebrook
Somewhat related, but how is K'nex doing these days? I was never a Lego child
growing up, I loved K'nex. The roller coaster sets, and everything else. It
just was easier to build really tall and elaborate structures without having
to have as many pieces.
------
f_allwein
Also interesting that the trademark for Lego bricks has expired. Does not seem
to hurt them too much though:
[http://edition.cnn.com/2010/BUSINESS/09/15/eu.lego.trademark...](http://edition.cnn.com/2010/BUSINESS/09/15/eu.lego.trademark/)
~~~
nevster
If you've ever had the misfortune to try any of the clones, you'd understand
why - they're crap.
There's a level of quality to Lego bricks and how well they stick together.
That and the quality of the designs. Those things are missing in the clones
I've tried. (Presents to my kids from well-meaning people.)
~~~
f_allwein
Weird though, isn't it? If the design is not protected, you'd figure somebody
would make bricks of the same quality for a lower price.
Business opportunity...?
~~~
tomjen3
Unlikely. Lego has spent a lifetime learning how to make the bricks really
well. Plus the only reason they are still around are their partnership - and
you can't make a star wars lego brick, no matter how good your tolerances are.
~~~
detaro
Mega Bloks (which seems to be the biggest compatible competitor) also has a
surprising range of licensed franchises, targeting both kids (e.g. Despicable
Me, Spongebob) and adults (e.g. Halo). Still nowhere near the market power of
Lego of course.
------
sandstrom
Reads like advertisement/PR-placement.
~~~
CyberDildonics
It absolutely is, I don't know how someone wouldn't notice.
------
rer
Why are Legos popular? Is it because they're like containers?
~~~
lj3
My nephew likes them because they're one of the few toys he has where he's
encouraged to take them apart and put them back together. He can play with
them as roughly as he wants. If they break, it's no big deal, just put it back
together.
------
splicer
So much plastic... they should release compostable Lego.
~~~
pjc50
The absolute volume of Lego is pretty small, and it's far more likely to be
resold than discarded because it has high resale value.
Lego that rotted would destroy the brand.
~~~
justusthane
Those bricks last _forever_ anyway, and they're almost indestructible. As a
kid I played with Legos that belonged to my parents growing up. Compostable
Legos is a terrible idea.
| {
"pile_set_name": "HackerNews"
} |
Avatar's green fascism - swombat
http://www.good.is/post/avatar-s-green-fascism
======
diego_moita
This is just too close to Godwin's law to be taken seriously.
"And what is fascism anyway? Good luck finding a concise or clear definition.
We are kind of foggy on that. Presently, the word is most commonly used to
cast aspersions on a particular political stance or belief. The implication is
that if you are fascist you seek to impose a vision of the world on a group of
people and that vision generally contains some notion of moral superiority."
What is the point of defining something as X if X can mean anything to anyone?
'Fascism' should mean a militarist, ultra-nationalist and authoritarian
political regime within a precise moment in history. If it can mean anything
than everything is fascist.
~~~
kevinpet
Fascism is an economic system based on government control of nominally private
enterprises.
If fascism is limited to the political regimes within a precise moment in
history, we lose a useful term.
~~~
_delirium
We also lose a useful term if we define it that broadly, though. It's not only
an economic system, but a complete political/economic system that comes with a
set of aesthetics and a particular focus on nationalism, a strong state, and a
strong leader.
Just government control of nominally private enterprises is much more common
than fascist regimes; it'd also include the UK in the heydey of the East India
Company, modern-day China, and even to some extent modern-day France.
~~~
elblanco
The problem with that definition is that it also defines rather well most
available instances of Communist states. So are you saying Fascism=Communism?
Or that those states are not exemplars of "real" Communism but are in fact
exemplars of Fascism?
------
teilo
As far as I'm concerned, once Godwin's Law has been invoked
[<http://en.wikipedia.org/wiki/Godwins_law>], the writer has lost all
credibility.
~~~
kscaldef
And, as far as I'm concerned, in this case you're the one being intellectually
lazy by making a knee-jerk rejection of the article on purely superficial
grounds.
I don't completely buy the argument being put forward here (it certainly
doesn't help their case that they at one point admit that they don't even know
what "fascism" means), but it's interesting food for thought.
~~~
teilo
Almost everyone who invokes Godwin's Law has a very reasoned argument why they
can connect the Nazi's to Topic X, that is nevertheless fully contrived and
meaningless.
I did read the article, thoroughly, and found the classic intellectual
laziness associated with Godwinesque arguments. And I quote: "Sontag’s point
is that the fascist sympathies and racial preoccupations that guide
Reifensthal’s work for the Nazis also can be seen in her photographic work on
the Nuba people in Africa. You can uncannily substitute Cameron’s name
whenever Sontag mentions Reifensthal and substitute the Na’vi whenever Sontag
mentions the Nuba. The entire Sontag article could just as well have been a
review of Avatar."
In other words, So-and-so is a Nazi. So-and-so wrote an article. Substitute
subject X for A and object Y for B, and it's practically a review of Big New
Thing XY. Ergo, Big New Thing is Nazi-Fascist propaganda. QED.
Hogwash. This is an example of the same intellectual ineptitude that equates
Obama with Hitler.
------
GiraffeNecktie
Ah yes, the Na'avi were athletic and the fascists were athletic, therefore the
Na'avi might be fascist. The Na'avi were sexual and the fascists liked sex, so
the Na'avi must be fascist. And yeah it was _really_ sinister the way they
preferred living in harmony with nature rather than turn over their home to be
strip mined. Sheesh. I'm so glad he pointed this stuff out.
------
Groxx
I think we can all agree on what Avatar means.
Pocahontas. In space. In 3D.
------
eplanit
I think the writer presents interesting, if perhaps over-intellectualized,
viewpoints. However, I don't believe him when he says he cannot find a real
definition of Fascism. I think that's deliberate, for if he included
conventionally accepted definitions, the rest of his article would be non
sequitur. I've always understood it to be a confusion on Patriotism, where
people align their beliefs behind the _government_ instead of aligning with
the principles of their country. Where principles are misunderstood, or
rejected, or under attack -- fascism takes hold. The word certainly has
nothing to do with athleticism.
In this more conventional meaning, I fail to make the connections that the
author makes re: Avatar.
~~~
CWuestefeld
I'm afraid the OP has it right here. From Wikipedia:
_What constitutes a definition of fascism and fascist governments is a highly
disputed subject that has proved complicated and contentious._
<http://en.wikipedia.org/wiki/Definitions_of_fascism>
~~~
lurkinggrue
One reason why I am likely it discount an argument that starts with calling
something fascist.
The word has been so misused as to be parody now.
They may as well amend Goodwin's law.
------
edwilliams612
Hey, I liked Battlestar Galactica too, but I don't want a religious nut bag
running the country based on her crazy visions...
I think the main thing to get out of this article is this:
"many people have reported feelings of suicidal depression after seeing it
because when they wake up the next day they realize that reality just doesn’t
measure up to Pandora."
Someone make an awesome 3d Avatar video game stat! Apparently the current
incarnation isn't enough and is leaving people suicidal!
| {
"pile_set_name": "HackerNews"
} |
Thank HN: for the help getting DigitalOcean into Wikipedia - niels_olson
https://en.wikipedia.org/wiki/DigitalOcean
======
niels_olson
I'm not even a customer, just a prospective customer, and 8-year wikipedia
editor looking for NPOV information, so I was surprised when the article I
wrote got deleted for lack of NPOV. I got a fair amount of help in the
deletion review, including a pointer to the googlecache of a previous
deletion, and additional facts about DO and some insight on how to maneuver
through a Wikipedia review.
| {
"pile_set_name": "HackerNews"
} |
Leap Motion designed a $100 augmented reality headset with hand tracking - tbassetto
https://www.theverge.com/2018/4/9/17208192/leap-motion-project-north-star-augmented-reality-headset-open-source-concept
======
codezero
Don't let the price fool you. The price is why I bought the original Leap
Motion hand tracker and I was so disappointed. The technology was very good,
but its design as a human interface device was abysmal. I am still really
confused why they thought it would be good to require that an interface be
created for every piece of software it interacted with, rather than allowing
that as an option but also having a consistent, operating system level driver
that worked across apps with a set of basic gestures.
I basically got no use out of it and strongly regret the purchase. That's the
catch though, the price was just low enough to make me not that enraged, kind
of like this thing here. Am I going to do it again? Oh gosh, I might.
~~~
jsgo
I'm kind of in the same boat, although in time I've gradually become less
negative about it.
I, too, was wanting something that felt like a native peripheral but always
found that it is a module you more or less have to hack a solution onto. I was
also a bit disappointed as I bought it during the leap year promo (nice job,
Leap Motion, nice job) mostly for the thought that the little block throwing
demo was usable for me. Apparently, VR only. And that's what I found: it is
meant only for the AR/VR space even though they positioned it for other spaces
(at least, after Windows 8 died. They did try to demo start menu navigation
via gesture).
That being said, I think the possibilities are there and I'd give strong
consideration to it. I'd rather see them partner up with the
Valves/HTCs/Googles/Microsofts of the world as getting into a common framework
is going to be pretty important for their tech to really catch on.
------
detaro
Official announcement post from Leap Motion:
[http://blog.leapmotion.com/northstar/](http://blog.leapmotion.com/northstar/)
------
melling
$100 hand-tracking by itself that worked really well would be valuable.
The entire gesture interface has stalled. Google Soli, for example, hasn’t
progressed:
[https://atap.google.com/soli/](https://atap.google.com/soli/)
~~~
detaro
The hand-tracking is probably the same module as in their existing products,
and those have been available <100$ for years now (although they've gotten
improvements over time)
~~~
melling
They’ve improved the hardware but never released a standalone update. They’re
focusing on AR and VR headsets.
They were talking about DragonFly a few years ago:
[https://www.roadtovr.com/ces-2015-leap-motion-co-founders-
ta...](https://www.roadtovr.com/ces-2015-leap-motion-co-founders-talk-
dragonfly-made-vr-motion-input-camera/)
------
jmeyers44
Leap Motion: What do developers want?
Developers: Hand tracking on mobile and an updated Android SDK.
Leap Motion: Ok, here's the blueprints to a PC tethered AR headset.
~~~
rasz
"Leap Motion sensor" is an USB 3.0 camera with clever driver, you can have it
on mobile when we start seeing USB 3.0 enabled smartphones.
~~~
leapmotion_alex
That's not a blocker. It's a USB 2 and 3 hybrid device, but we never actually
rolled out USB 3 in the firmware (would have raised the minimum spec too high
for too many people with almost no benefits), so it runs on USB 2.0.
------
83457
I'm assuming the general idea is that multiple layers of depth perception are
not necessary if everything rendered is at very consistent range such as at
your hands in a natural position? Reminds me of the early oculus ducktape
prototypes vs VR headsets that cost tens of thousands of dollars. Limited
capability but straight forward and cheap in comparison.
------
corysama
I had assumed these videos of wearable UI (pictured in the article) were
recorded on a Meta-2. Now I guess we know better.
[https://mobile.twitter.com/keiichiban/status/968534116420513...](https://mobile.twitter.com/keiichiban/status/968534116420513792)
------
andromedaworld
That's incredibly affordable. These guys are impressive. I especially like
that they're software centric and they're interested in plugging into as many
devices as possible.
------
josephpmay
They made some really interesting design choices that prioritize optical
quality over every other factor (ergonomics, look, etc.). Really interesting
approach to create a device that’s esentially only for UX prototyping. Cudos
to the Leap Morion team!
~~~
vokep
I think it does make sense. VR content is still lacking and will be until the
basics are figured out. Right now the most important part is getting content
out there. With current gen stuff, we have pretty good hardware already, but
not much content, and part of that is because the hardware is expected to
advance quickly. It makes sense as a game dev to wait for the basic hardware
of a 'VR headset' to be figured out.
Right now, there are so many potential questions: Should players be assumed to
have foveated rendering? for good vr content, probably, however few headsets
have any kind of FR yet.. Should players be assumed to have a certain
resolution headset? maybe, maybe they have high res screen but GPU can only
push it at lower resolution? How to handle text in a situation like this?
Degrade the experience of high resolution users by making all text yuge?
Ignore those with lower resolutions entirely?
Basically, I think content is best developed right now with a very high
standard of technology. So its better to have clunky, uncomfortable, but very
powerful headsets right now, so developers can create great content. Some
articles will still be written about how 'VR is dead!' until after awhile
someone releases a comfortable AR/VR headset with high resolution and foveated
rendering and it turns out theres a trove of content waiting. When that
happens, VR will truly be born. VR IS dead right now, because it has yet to
begin its life truly.
------
toastking
So is part of the idea of releasing the schematics that it might push VR
headset makers to adopt a design similar to this?
~~~
josephpmay
No. The idea is that UX designers can use this to prototype for future AR
headsets
------
Analemma_
I'll believe it when I can buy it. For the last eight years, Magic Leap has
produced a lot of hype and no product.
~~~
tbassetto
This is about Leap Motion and not Magic Leap though.
~~~
jsgo
haha, I made the same mistake in reverse though when I was underwhelmed by
Magic Leap due to the Leap Motion controller I bought.
I guess that it is both companies have "Leap" being the non-modifying sounding
word in the name and being in the same space? I feel bad for both that the
confusion is there.
| {
"pile_set_name": "HackerNews"
} |
Why You Shouldn't Interrupt a Programmer - libovness
http://heeris.id.au/2013/this-is-why-you-shouldnt-interrupt-a-programmer
======
calineczka
Once upon a time I was working with a very challenging legacy code and I was
building similar constructions in my mind. The office was sometimes noisy and
chance of interruption was not that small. So I established a habit of writing
kind of stack trace of my own thoughts so that I could easily come back to my
state of mind after such thing. It looked like:
There is a bug in module X
Module is X is calling module Y when user is not yet activated
We are creating user subscription
We are using current subscription in subscription creation
Current subscription is A when user is not activated
Current subscription is B when user is activated
Probably bug in method c()
Think what is going to happen in situation M when changed the implementation to d().
The list sometimes had 12 elements that I was trying to fit in my head to find
the solution to the problem. I now work remotely from home (quiet and all
that) and most of the code that I work on is of much better quality (another
company, better practices) but I still sometimes resort to this method when
working on a complicated piece of code that is unfamiliar to me.
~~~
Maxious
This is a common technique in engineering troubleshooting
[http://en.wikipedia.org/wiki/Ishikawa_diagram](http://en.wikipedia.org/wiki/Ishikawa_diagram)
[http://en.wikipedia.org/wiki/5_Whys](http://en.wikipedia.org/wiki/5_Whys)
~~~
calineczka
I never thought about it as something that can have such fancy name and such
broad engineering application. I think my technique is like 1% of what
Wikipedia describes.
------
jimbokun
I liken programmers to extremely expensive equipment for manufacturing
software.
When a company invests in expensive equipment like that, it is very important
to keep it producing output. So by sending programmers to meetings, your
expensive equipment is sitting idle, offline, producing nothing.
Interruptions are like shutting down an entire assembly line. When you turn it
in again, it will take time to be running smoothly again.
So to the managers and executives, it is your choice how to utilize this
highly specialized, very expensive equipment. You can try to keep it running
at full capacity, or frequently start it up and shut it down, take it offline,
and leave it sitting idle.
~~~
zanny
Many programmers (at least me) have varying levels of peak output in a day.
Some times I literally can't make my brain work after 2 - 3 hours of in-the-
zone work. I just can't read lines off a screen anymore.
Other times I can go 24+ hours without breaking a sweat.
I think in practice your average programmer can't operate on the 40 hour a
week traditional work schedule and actually output solid performance for all
40. On average, at least. So maybe the first businesses to start introducing
meetings and such were attempting to pace their SE staff and actually saw
positive results, since they still got whatever the maximum output one
engineer could put out before their brain went to mush in a week but also had
them talking to clients or discussing other things.
It is just the industry latched on to bureaucracy without postulating why it
might be useful. You want your SE coding whenever possible.
~~~
aidenn0
This is the reason why my productivity has gone down since going from single
to having a family. When I was single, I would just cut out early on the days
I wasn't in the zone, and get some errands or housework done.
When I was in the zone, I would stay at work until right before I would go to
bed.
This way I would spend nearly all of my "in the zone" time doing work.
Now that I have kids and such, I leave at 6 every day regardless of my
productivity level, so even though I spend only slightly less time at work, my
net productivity is way lower.
~~~
javajosh
Anyone can take a great photograph. The professional photographer learns
techniques to take great photos more frequently.
In a sense, "professionalism" in any field implies a certain "frequency of
success". For a programmer, that means learning techniques to accomplish tasks
even when you aren't "in the zone". This means learning to get in the zone,
how to stay in the zone, and learning to produce when you're nowhere near the
zone. This requirement is universal to all professionals, including all
_professional programmers_ [1]
I would add that learning to approach your work even when you don't feel like
it can sometimes yield surprising insights. Your brain is recoiling from work,
but only as it approaches it from _certain directions_. It is possible to
approach a problem from other angles, and getting "in the zone" from another
angle can sometimes yield unexpected improvements to the product for the
simple reason that you're looking at it in a new way.
[1] There are two categories of professional programmers, the hired guns and
the artists. They both want to build great things. The hired-gun wants to
build things faster and to spec. To him, "great things" is unambiguously
defined as 'the things that will satisfy the customer'. All businesses love a
speedy, accurate programmer - especially if they can be speedy and accurate in
a non-disruptive way. Such programmers are very good at understanding existing
codebases, processes, and doing the minimum work to get the job done. Often
they simply do not care about technical debt - (indeed, they are incentivized
the other way, to maintain (and even increase) technical debt, every bit of
which only improves their negotiating position with the client.)
Meanwhile the artist-programmer success is not defined by conformance to a
spec. Success is harder to define - but the artist can define success as
getting the time to _perfect_ his creations, traveling ever higher up that
diminishing returns curve, going higher than most people are willing to go.
This kind of programmer is the dreamer, the architect, the creative. This can
be a backend architect, or a front-end perfectionist. They share the common
goal of _mastery_ and _beauty_. Most, if not all, programmer heroes come from
this category. And rightly so, I think.
~~~
sateesh
Nicely put. Yes, programming is part art and we are not like machines that can
work no matter in what state we are. But often we mask our
procrastination/laziness blaming it on lot many things and waiting for a right
moment to magically arrive get the work done.
I am reading 'Dune' now and I found this advice from Halleck to Paul so
relevant :
'I guess I'm not in the mood for it today' Paul said.
'Mood ? Halleck's voice betrayed his outrage even through the shield's
filtering.
_' What has mood to do with it? You fight when the need arises - no matter
the mood! Mood's a thing for cattle or making love or playing the baliset.
It's not for fighting' _
\-- Dune, Frank Herbert
~~~
Mithaldu
While this applies to many things people do, i don't think it applies to
programming. Programming is a continuous activity of concentration done over
the course of 8 hours, 5 days a week, roughly 45 weeks a year. Meanwhile
fighting of many kinds is something that happens in short bursts of extreme
focus and excertion.
In fact, programmers have to "fight" too, and it is highly different from
their daily work: It is when the software is burning cash and they have to
find the problem and implement a fix right now. Most programmers find that
they deal with that extremely well, though it usually happens at the cost of
the rest of the day.
------
jtheory
This isn't applicable to only programmers, of course; my wife is a novelist --
there are a lot of high-level concerns that she needs to balance in her head
PLUS there's the fiddly nature of creative flow, and it all comes crashing
down all too easily.
I had creative aspirations when I was younger (writing and music in
particular), and came to programming because it's far more predictable; the
costs of interruption are bad, but interruptions can be avoided, and the
difficulties can be mitigated (e.g., I take notes for anything complicated,
and re-read them when restarting a task; I break compilation as a to-do list,
and/or use version control for non-compiling code). Flow is really important,
but I generally _know how to do it_ \-- get enough sleep, clear away
overhanging stress clouds (like "taxes are due soon"), eat well, break tasks
down, get the smallest possible thing working, iterate, and so on).
But creative work killed me -- it was so painful to do iteratively; I'd spend
8 hours "writing" a poem that actually didn't coalesce until the 7.5 hour
point, at 4am. Composing a bad first draft of anything left me feeling
horrible; I never managed to force my way through that as long as I was trying
to make it "what I did".
Now that I do something else primarily, I can noodle around creatively and get
much more joy out of it -- but those years left me with much more respect for
people doing more creatively-oriented mental work than I do.
~~~
eru
Look up writer's discipline. `Creativity' is not too different from coding.
> \- get enough sleep, clear away overhanging stress clouds (like "taxes are
> due soon"), eat well, break tasks down, get the smallest possible thing
> working, iterate, and so on).
That's great for writing a novel, too.
~~~
jtheory
It's not that these things don't _help_ creatives, but that they are not
reliably sufficient to produce something of value.
If I'm coding on an uninspired day, I can easily just shift to tasks that I
know are simpler, and create a perfectly workable (if boring) solution. I can
work my way through to finding even fairly subtle bugs just by stepping
through the logic; it's slower than a flash of insight, but it works.
A writer or other creative person with high standards must discard all of that
uninspired work. In theory it may help keep the ideas churning, but for most
writers I know it can be a frustrating grind when things just aren't quite
clicking. It certainly helps to "train the muse" by writing every day at the
same time, always filling the page (even with nonsense if that's all you can
produce), and so on, but at the end of the day, they can't say "well, this is
a shitty story, but it'll pay the bills". It won't.
There's also the psychological difficulty that comes with putting sometimes
_years_ of work into something that may actually have no monetary value, or
minimal. There are obvious parallels to building a startup, except that novels
that succeed can't naturally be built into sustaining income -- you have to
start another novel, and it can easily earn you nothing after 5 years of work.
~~~
eru
In eg writing, there's lots of rewriting and editing. (And in coding, there's
lots of truly inspired work, too.)
------
tmikaeld
[http://i.imgur.com/xvNRKIT.png](http://i.imgur.com/xvNRKIT.png)
~~~
aw3c2
I downvoted you before I realise you just provided a copy of the actual post.
Please include some context next time and not just dump an imgur link.
~~~
lignuist
So you downvoted something that you did not even look at?
~~~
bdg
A post that expresses little thought should be down-voted. The post in
question is of value since the original link 503'd, but that value is
obfuscated to some by the lack of a quick "Here's a mirror" explanation.
Is this really a big deal?
~~~
ygra
Back when I first tried opening the page it 503ed and there was just one page
of comments, one of them was this image link. Its purpose was fairly clear,
actually. And helpful.
~~~
strickjb9
No it's not clear but it was helpful. There is an implication that a simple
imgur link could be a mirror of the comic image. But then you would have to
know that the content of the article was a comic image.
------
nmeofthestate
This scenario is a bit optimistic. I made a cartoon depicting my open plan
office experience: [http://imgur.com/fsv1cCq](http://imgur.com/fsv1cCq)
~~~
switch007
That's so accurate! The penultimate one should be putting on ear phones, then
the last one showing someone coming over to your desk and interrupting :P
~~~
rix0r
I actually made one about that :)
[http://rix0rrr.tumblr.com/image/42866777562](http://rix0rrr.tumblr.com/image/42866777562)
------
teddyh
Reminds me of this:
Don't Wake Up the Programmer!
[http://alexthunder.livejournal.com/309815.html](http://alexthunder.livejournal.com/309815.html)
~~~
brador
That article contains the best analogy of programming I've ever found.
Beautiful piece, thanks.
------
ohwp
This is also why you shouldn't interrupt yourself ;)
Turn off your e-mail client, phone, messages, internet connection, HN.
~~~
option_greek
IMHO, while working on challenging tasks (bugs mostly) where we are not able
to figure out something, tiny breaks spent on unrelated subjects seem to help
a lot. While interruptions are bad, a badly timed interruptions seem to be the
worst.
~~~
sateesh
In my experience tiny breaks away from the workstation are far more helpful
than the ones that need you to use the computer. I have found taking a break
from a programming session in form of checking HN, twitter makes the mind all
more muddled.
~~~
gbog
Yes, let's grab a cigarette... or a coke, or a coffee. But all these circuit
breakers are bad for health. The best I found out for now is to add hot water
to my tea mug.
~~~
ljf
Or starjumps in the corridor
------
jenrzzz
Mirror: [http://heeris.id.au.nyud.net/2013/this-is-why-you-
shouldnt-i...](http://heeris.id.au.nyud.net/2013/this-is-why-you-shouldnt-
interrupt-a-programmer)
------
jmadsen
The problem is, the only people who ever read these are other programmer who
already know this.
Need to find places where we can post it to NON-programmers
~~~
hkmurakami
I'm currently back in school in a non-programmer environment, and I honestly
have a hard time bringing this sort of this up to most people I know here
because I just know that they won't understand why this is so important and I
just don't want to deal with the interpersonal mess :( :(
~~~
mhurron
Apparently programmers are the only people who think about problems. You poor
little unique flower.
Write it down. It will be clearer to you. You can more easily refer back to
it. You will be interrupted. You will need to do other things before you
finish your current grand opus. You will lose your place in your own thoughts
just by trying to hold it all in your head the whole time.
~~~
icebraining
You're right, though your post would be better without mocking people.
I don't have an habit of writing stuff down, but I know I really should. That
said, a couple hours of interruption-free work doesn't seem an extravagant
request.
------
lotsofcows
Needs a clock in the background to hammer home the point to non-programmers
that it can take an hour to get from the 1st to the 6th panel. Bosses take
note: an hours work has disappeared.
~~~
goshx
I agree
------
Pxtl
This is also why, as a programmer, it's essential that you manage and handle
your email. If you're not available by mail in a _vaguely_ timely fashion,
you're going to get people learn to workaround your deficiency by chasing you
down in-person or over voice.
~~~
andy_adams
Wow, this bit of wisdom is unbelievably valuable in my experience. The number
of programmers who have _thousands_ of unread messages in their inbox has
always startled me. So many of them don't respond in a timely manner via
email, which earns them the title of 'flake', and opens them up to phone calls
and other interruptions.
------
rix0r
To my mind, the cartoon is more of a depiction why you should avoid mutable
state and non-local effects.
~~~
colanderman
Or moreover, why you shouldn't write parsers/lexers by hand.
------
ozh
Will show this to the wife. She has a hard time understanding why working on
week-end projects by 45 minute chucks isn't effective as I need 20 minutes to
get in the zone and restart my thoughts where I left them
~~~
gbog
There is one nice way to push oneself in the zone faster: just open a broken
test in your test suite, it will point you to the next step. [edited to
clarify]
~~~
keyle
I quite often leave my code broken so that next time I open the solution I
know exactly where I left off. I will often leave a comment there or
throw("get X to do Y now")
~~~
jtheory
I do this as well -- once I have the complete solution to something in my
head, I quickly go through the various parts of the codebase that will be
affected and drop pseudo-code or even just rapid notes in each place -- which
will intentionally break the compilation, so that I can use the compiler
errors as a fast & direct way to pick up the threads again if I'm interrupted.
For non-compiled code I'll add a dozen line breaks and a note in all-caps to
make it jump out in a diff.
~~~
gbog
Great but using tests is better, because written correctly you will keep them
and they will check forever that the thing is working
------
stef25
Whenever I try to explain this to interrupting colleagues / bosses I always
get rolling eyes and "here he goes again", frustrating as hell.
~~~
hkmurakami
This is why I haven't been able to bring this up in my new environment
(school). I know that people won't get it, and I just have a strong desire to
avoid the admonishment :(
------
SubuSS
Late comment but: I look at it as a necessary evil. I usually solve it by
having a note of the intermediate understandings / thought process on OneNote
when I am debugging something deep. It probably takes 2 minutes to get back on
the train when disturbed. Yes - I do debug production systems / file system
level issues / Storage level issues etc. And yes I am a senior engineer who
keeps getting walkin / IM requests.
The flip side of saying no to meetings/walk ups is that the senior won't be
doing a good job of unblocking the team. It is a huge waste to leave a bunch
of junior engineers solving the same issues that you had solved years ago.
Mentoring takes a hit and morale takes a dive in that case.
------
steven777400
Every month, I produce a "time usage" pie chart for one of my managers for the
month. At one point, he said: "You need to spend less time in meetings."
So I told him I'd be happy to oblige if he wouldn't schedule me in as many. He
was shocked and said most of the meetings must be from my other manager (who's
a real hands-off kind of guy). So I broke out the details and showed him that
the vast, vast majority of my "meetings" time was scheduled by him.
He didn't bring it up again, but also continued to schedule me in as many
meetings as before... So I guess that's a decision. :)
~~~
brudgers
Obviously, he wouldn't schedule a meeting if he didn't think it was important.
I suspect there is a correlation between managers who believe their meetings
are important and managers who believe that an hourly breakdown of a direct
report's work tasks is a more meaningful metric than the direct report's work
output.
------
bmelton
Worth noting, but this article is _also_ a plaintiff cry for why programmers
need to write better comments, too.
Edit: I meant _plaintive_ , but my eyes were still crusty with sleep, and I am
a giant dummy.
~~~
ChristianMarks
Who is the defendant?
~~~
bmelton
Gah. S'what I get for posting before coffee. It should read "plaintive".
------
jseban
This is also why you should use pen and paper and not try to keep everything
in your head?
~~~
jpatte
The main problem of pen+paper is it's only 2D. Modeling an entire process may
require a lot more than 2 dimensions, so trying to put it in 2D is actually
harder than modeling it freely in your head.
~~~
tempestn
Exactly. And much slower as well. Obviously if you _expect_ to be interrupted
you can take the time to download your brain onto paper, but trying to do all
your work on paper would be like running your CPU through a printer->scanner
loop-back.
------
kineticfocus
lol... the current page works as a punchline just as well:
_Service Temporarily Unavailable
The server is temporarily unable to service your request due to maintenance
downtime or capacity problems. Please try again later._
------
waylandsmithers
I don't mean to be a downer, and I certainly enjoyed this comic, but I fear
that these are the kinds of posts that lead to communities becoming nothing
more than memes and other quick laughs on reddit.
~~~
moccajoghurt
Well this was very specific programming related joke. If they stay like that
and only pop up once in a while, it's fine. Just enjoy the joke and stop
worrying.
------
tieTYT
As a test I sent it to a non-technical friend. She said, "I don't understand".
In other words, this only makes sense _if_ you're a programmer. I feel the
cartoon's pain, but I can't send this to a manager to help them understand.
------
niravshah
This is why programmers (and everyone doing deep analysis/critical thinking)
get a huge benefit from taking notes.
------
jipumarino
I got a 503 error and for a moment I thought it was very insightful.
------
strickjb9
I showed this to my wife and she didn't get it right away. I explained it to
her then she said 'Does this mean I need to go?' because we were gchat'ing and
I was working at the time (aka waiting for Eclipse to respond). I regrettably
told her that we need to wrap it up.
------
wiremine
This is great! It articulates what most of us programmers feel internally when
we're interrupted. What's I'd also love to see is a cartoon explaining the
external effect of an interruption. Like, when you interrupt a programmer
you're pulling the "stop" cord on an assembly line: it doesn't just effect
that individual, but there is a net effect on the overall effort.
(FWIW, I don't think the assembly line is a good example, because programmers
work in parallel, not in sequence, but it's the best sort-of-example I could
think of on a Monday morning...)
------
tluyben2
For me this image shows why there is something deeply wrong with programming
at this moment in time; the fact you need to do all those assertions/logical
operations in your head instead of the super computer standing in front of you
(which is much faster in most those operations anyway) is painful to see. By
clicking that line, the IDE should generate all that context (and
graphs/charts/whatever) for you in a jiffy instead of you doing that in your
head.
~~~
jdbernard
Sure, if you are content with the way the compiler lays out the information.
Personally, I am far more efficient with vim and a CLI than Visual
Studio/Eclipse/$FancyIDE precisely because I can live in my head and not in
the IDE.
The day we can replace the mental process required to fully understand a
problem is the day we can put down our keyboards and let the computers do all
the programming for us. Until then I assert that you will not produce the same
quality of code without doing the hard work in your own head.
~~~
tluyben2
I'm looking forward to that day anyway. And I agree to some extend with you as
you say 'doing the hard work in your head', I just don't think _all_ the hard
work should be done there. Just the hardest work computers cannot do for you.
I work with vim only because I don't think IDE's contribute much at the
moment. I believe they should be able to contribute a lot more. I'm just not
sure how that is supposed to look, but luckily smarter people than me are
working on that :)
------
tmikaeld
Someone put it on 9gag
[http://9gag.com/gag/av0z0Bn](http://9gag.com/gag/av0z0Bn)
------
cburgmer
I disagree with what I think this picture implies. That is shielding the
developer from interaction makes him/her more productive. In contrary,
interruption and conversation belong to development. The more my fellow
developer colleagues talk, the better the code base is.
~~~
pwelch
Yes and no. Yes, talking can help bring a lot of people to a solution easier.
Taking a coffee break and chatting with a co-worker about your current problem
or pairing with another set of eyes is often vary helpful.
However, when you are really focused on a complicated problem it is hard to
find a solution when your thought process is constantly interrupted.
------
Delmania
Unit tests can go a long way to helping both gain and retain understanding of
what a codebase does. Context switching topics is an important life skill. A
work place that's free from distractions would be good, but that's not always
possible.
------
elwell
The number of upvotes is indicative of a common thread of frustration felt by
programmers.
------
djKianoosh
A lot of the commentary places importance on getting stuff done in a single
day...
I think sometimes we overlook that really strong problems require many days of
active/passive thought. Soooo, sometimes interruptions are good!
------
NAFV_P
Let's face it, coders can't multi-task.
Fortunately, computers can do all that for you.
~~~
bradwestness
_Humans_ can't multi-task.
~~~
NAFV_P
It's a myth invented by (sociopathic) business gurus. It holds as much H2O as
"soggy biscuit".
------
LeSeb
Being a programer on trading floor, this happens all the time ...
------
SworDsy
It's still funny that now it's a down
------
gouggoug
How ironic is it that when I clicked on "Why You Shouldn't Interrupt a
Programmer" I got a 503
------
rsobers
My only qualm with this comic is that it doesn't end in a fit of rage. :-)
------
known
Writing software != Selling software
You need mutually EXCLUSIVE skills.
------
umrashrf
I can't access the page.
------
Spoygg
Excellent :)
------
tmikaeld
hacker news effected the site
~~~
jrgnsd
affected?
~~~
Ygg2
Eh, no need to call in the Grammar Squad. Not to mention effect is correct
here (effect means ‘to bring something about as a result’). Hacker News did
bring something about as a result.
~~~
jmmcd
Grammar Squad here with the facts. And just the facts.
When _effect_ is a verb, the object must be the change itself, similar to
_cause_ : "Hacker News effected a significant deterioration in site
availability". With _affect_ , the thing being changed is the object: "Hacker
News affected the site."
~~~
shangxiao
What nobody's quoted xkcd yet? [http://xkcd.com/326](http://xkcd.com/326)
~~~
jmmcd
Very good, but the Grammar Squad are not amateurs, and we have not been
tripped up!
| {
"pile_set_name": "HackerNews"
} |
Ask HN: Potential employer is asking about 'education', I'm a college drop-out - pedalpete
I thought this was a bit strange, but I've applied for a position with a large and amazing software company. I don't normally put anything on my resume for education, as I dropped out of University after two years, and I don't think anybody has ever asked. My work experience has always spoken for itself.<p>Any suggestions on how to handle this? I'm thinking about adding a section that says I've been continuously learning through my work experiences and other opportunities.<p>what has worked for you in the past? or what would you think would work?
======
patio11
I'd leave it off the resume rather than putting anything on the resume which
will be read as "Education: Why I Don't Have A Degree". If someone asks about
it in person, "I left $UNIVERSITY to pursue other opportunities." and then
steer the conversation back into happy territory.
If someone won't hire you for lack of a sheepskin, their loss; plenty of
companies have no such aversion in the current environment.
------
__ingrid__
I am in the same boat as you (dropped out after 2 years, then started working
full time). I prefer to leave it off my resume because I like to address it
myself in conversation (also I know who cares based on who asks), but honestly
either way works. So long as your resume is not barren I do not think it is
that big of a problem to leave it off.
As far as responding to their question, just be confident and direct. "I left
university because of X, and I do not plan to complete my degree at the
time/until I do Y/whatever". The reason you give will be a lot better than the
possible reasons they might think up, so do not worry about it. There are many
legit reasons for dropping out, including that it just was not for you, all
they want to know is that you did not drop out because a personal flaw that
may make you a bad employee. If you dodge the question, give a fishy response,
or make too many excuses, it may seem like you have something to hide, and
they will start speculating.
One last thing, do not put too much weight on this question. While I
personally do not want to work for a company that has a strong degree bias
either way (I left my last company, which I otherwise loved, on a sad note
because of this), I do not think that this is that a definitive indicator that
a company looks down on people without degrees. I have found that sometimes
either someone who is not that technical and who's opinion is not that
important (HR person or recruiter) is asking because they do not know better
and are just compiling information for a higher up who did not specifically
ask about your education, or sometimes an interviewer will ask it because they
want to know how you will respond (whether you will be silly and apologize, or
be confident in your skills, what's your view on education, etc). It is one of
those questions where you can just say "No, I did not graduate" and it is not
a big deal and you move on, or you can start to sweat, give a long winded
excuse, and make your interviewer worry. If they do have a degree bias and do
not hire your for that reason, well, then you dodged a bullet.
------
Wajeez
I've been around long enough to tell you that when an employer is judging you
based on your education, this company is so boring, most probably run by
academic heads who will bore you to death.
Run, run for your life, Steve Jobs and Bill Gates, among many, are also drop
outs.
~~~
pedalpete
That's the crazy part. The founders are both drop-outs too!
~~~
eshvk
So I am confused here: Are you being asked in an application form to list your
education? or Is this during an interview call/email?
If it is the former, I wouldn't think too much about it. People probably use
standard forms for these purposes. If it is the latter, just tell him that you
did school for some years and decided your time could be better spent outside
school.
~~~
pedalpete
after the recruiter saw my resume, they asked about my education, I was just a
bit surprised. I updated my resume to show that I dropped out, but also that
I'm a continuous learner. Hopefully that works.
Thanks for your help.
~~~
eshvk
It is a standard recruiter question. Don't worry too much about it. I am not
sure there is a company wide policy to ask these questions or not.
P.S: For future reference, the best thing to do in this case it to mention as
part of educational experience maybe the relevant courses you have taken and
the amount of time spent at school. (If you need mention it at all).
------
gregpilling
"Some College" is what my sociologist wife calls my non-complete university
education. As an employer myself I care more about what you can do for me than
what institution you did or did not go to, and what studies you did or did not
complete. However, do recognize that education is an easy data point to fixate
on if you are a recruiter.
THe things I am trying to hire for are not offerred as a university degree
anyway. Maybe this is not true of where you are applying, maybe it is true.
ALways tell the truth and don't be afraid of the choices you made. Own them if
possible.
------
brudgers
If you are going to add "Education,"
Just be honest.
List your high school.
List the number of hours completed and the university.
Some people will make an issue of it.
Some won't.
Good luck.
| {
"pile_set_name": "HackerNews"
} |
A Robot That Climbs Walls - toni
http://www.unews.utah.edu/p/?r=080310-1
======
brianbreslin
they should put a video of it, and if there is a video, make it easier to
find.
| {
"pile_set_name": "HackerNews"
} |
IPFS: The Permanent Web - adefa
http://ipfs.io/
======
greenyoda
Extensive discussion of IPFS from yesterday:
[https://news.ycombinator.com/item?id=8069836](https://news.ycombinator.com/item?id=8069836)
| {
"pile_set_name": "HackerNews"
} |
How CRE made SEOmoz $1 million - bearwithclaws
http://www.conversion-rate-experts.com/seomoz-case-study/
======
mathewgj
The best thing about this post was the case-study description of the full,
'first principles', customer development-type approach to landing page
optimization including lessons learned from face to face selling, and a
handful of very specific surveys and customer conversations. Usually, these
kinds of case studies focus on either landing page opt. or customer
development, but don't put it all together.
------
patio11
This is one of the best content-to-sleeze-ratio posts you will _ever_ see
about Internet marketing.
------
kirse
My favorite part of the whole sale page (that this article did not point out),
was the cutesy little "Warning!" at the bottom that tells people they are
absolutely going to be _OVERWHELMED!_ by the amount of tools and features
they're going to get...
I actually first noticed this sales technique in one of those late-night fat-
loss commercials where the chick starts out by saying "WARNING: Hydroxycut (or
whatever) is only for people who need to lose a _serious_ amount of weight and
should _not_ be used by average dieters!"... absolutely brilliant.
------
gstar
I initially missed it, but the page itself is at
<http://www.seomoz.org/pro_landing.php>
~~~
muhfuhkuh
What is it about these "clickbank"-type self-contained pages that purportedly
lure so many to part with their cash? Anyone that have one of these long-ass-
single-page-big-bold-font-with-testimonial-blurb pages explain the allure of
these things? What is the attraction? Is it the big bold typefaces? Is it the
shill-y feeling testimonials? I have to admit, it does stir something non-
negative in me to read on, but I just can't quantify or describe what it is
I'm feeling. It's kinda like an attractive revulsion to it. Weird.
There's a gotta be a study on the efficacy of these pages, I'm sure; but I bet
I'll have to pay $19.95 to read it.
~~~
petercooper
One of the biggest keys to the technique is the headlining. If you look at a
typical geek blog post or article, you'll get a title, then perhaps a few
subheads with paragraphs of text in between.
In these long sales letters, you get perhaps 10-30 different "headlines" all
the way through the piece that, on their own, attempt to sell the product.
These pieces are ridiculously easy to scan and use either positive, targeted
language, keep asking questions (a key tactic), or allude to interesting
things within the rest of the content or in the actual product.
Examples from the SEOMoz page:
_"When eBay, Disney and Marriott need SEO help, here's what they do..."_ (you
want to know what that is now, right?)
_Boost your website’s rankings within 30 days–Guaranteed_ (Hmm.. these guys
look legit and they're making that claim? They must have something serious
going on.)
_We’ll give you the tools you need to quickly boost the website rankings for
any website – on demand._ (Speaks for itself. This is one helluva promise.)
_Every month, ask your burning questions to our team – and get prompt expert
replies_ (So even if I don't understand the product, I can ask about it and
know these guys are keen to give me a response.)
_Plus, get these 8 must-have SEOmoz PRO guides—worth over $250_ (A classic
_dirimens copulatio_. Learn more about this at
<http://www.copyblogger.com/but-wait-theres-more/> \- they've already
convinced you the product is cool but now they're piling up the perceived
value so they can gently hit you with the price..)
------
msg
I appreciated the self-referential nature of the page.
1\. We created a web page long enough to tell the story
2\. We infused the headline with curiosity rather than overt "buy me" language
5\. We augmented the message with video
Et cetera.
If it works for SEOmoz and CRE...
Awesome marketing and meta-marketing.
------
falsestprophet
And there is a negative option $1 trial, $79 monthly rebill: stay classy
SEOmoz.
~~~
rarrrrrr
Did you read the article in detail? It's clearly and unambiguously
communicated as a $1, one month trial, as a way of offering a minimal risk
option to people who might like to try but are unwilling to risk the $80 they
charge upfront.
~~~
falsestprophet
Yes. The $1 one month trial is automatically followed (the negative option
part) by a monthly $79 charge (the rebill part) unless the user cancels by the
29th day of the trial.
A (usually large) proportion of customers will be confused and unintentionally
pay for at least one month of full priced service: perhaps they don't
understand they need to cancel before the 30th day, perhaps they forget to
cancel, perhaps they try to cancel and fail.
There is a more honest alternative. Amazon Prime requires user input after the
trial before their first $79 subscription charge is made. This is called
positive option billing.
~~~
apowell
There is absolutely nothing dishonest about clearly communicating to the
customer what you're going to do, then doing it. You may run your business
differently and wish others did the same, but that doesn't make intro pricing
dishonest. This is doubly true when you're marketing to internet marketers.
~~~
_delirium
To me, if the intent and main effect are to basically trick people into paying
for something they don't really want, it's at least sleazy, if not outright
dishonest. There are legitimate uses for trial offers, so it's a bit of a
judgment case, and I think depends to a large extent on just how clearly the
terms are communicated. In particular, it should be very clear to customers of
average sophistication exactly what will be rebilled, and exactly what they
need to do to avoid the rebill if they'd like to cancel--- and the cancelling
should be easy.
~~~
lena
I agree. If you genuinely feel that your product is worth the $80/month and
that your customer will feel the same way, why not send them a reminder a few
days before the trial stops to let them know? Maybe give them a freebie if
they continue the membership.
I used to have a subscription to a UK magazine where apparently automatic
subscriptions are not legal, so they have to sell you the magazine again,
every year. I thought this was great, as opposed to the situation in the
Netherlands where you have to cancel at the right time, or else you are stuck
with another year. (There are laws in progress to change this, so clearly many
people are annoyed by it)
------
petercooper
_We of course knew that a $1 offer would boost subscriptions but the real goal
was to keep these users active beyond the trial period._
I suspect it didn't work. I just did a search and I got this e-mail back in
February 2009. If the $1 idea had worked, I'd expect them to still be running
it. (It'd tempt me to upgrade my account, I think. I've considered upgrading
to PRO but keep putting it off as $70/mo is a lot for something I might not
have the time to tinker with.. I think I need to get a better "live" feel of
it to be sold on the tools.)
~~~
josefresco
I paid the $70/month and dumped it after a few months. I just wasn't using all
the tools to make the cost worth it (an issue of time mostly). And to make
matters worse a lot of the tools simply didn't apply to how I sell my
services/do my business.
I do know that given the time and investment I could get good value out of the
services but for now it's just too much to spend each month it goes under-
utilized.
------
aresant
This article points out exactly why the "above the fold" debate is an absolute
MYTH when you're building a sales page with a specific function.
In my experience length wins out 99% of the time.
~~~
mindaugas
I've always wondered why almost all(relatively speaking) affiliate marketers
use long pages - Sales pages. Now I know why.
~~~
aresant
If you've got a site and want to test a long-page ad, here's a template that
works pretty well:
\- Here’s what I got: Just say what you have, don't sugar coat or spend a lot
of time dancing around.
\- Here’s what it will do for you: what problem are you trying to solve?
\- Here's what it did for other people like you: testimonials.
\- Here’s what to do next: Just come right out and ASK for the money, tell
people what to do. Don’t ruin the close.
~~~
blasdel
You're implying that it's written in the first person, but you're missing the
gif of the entrepreneur character's signature at the bottom right above the
paypal button :)
~~~
aresant
LOL - spot on ;-).
What's interesting though is to observe a monster organization like Fool.com
leverage this exact same style - it scales, believe me!
------
paraschopra
I have personally interacted with Conversion Rate Experts and they are a
fantastic team, solely dedicated to the art of conversion rate optimization.
They do their job excellently and as you can see from this post they write
great content too!
Really well done, Karl (from CRE) - if you are here on HN, that is.
| {
"pile_set_name": "HackerNews"
} |
Play with these js physics - becasual
http://lonely-pixel.com/
I believe this site be made in jquery also can anyone tell me if it is using a static web generator like these?
https://iwantmyname.com/blog/2011/02/list-static-website-generators.html
======
czbond
Wow - that is really a good job. The tear-able cloth is amazing. I also loved
the rain drops.
~~~
becasual
its not my website, I thought I will share my finding with others
| {
"pile_set_name": "HackerNews"
} |
Libc++'s Implementation of std::string - stuffypages
https://joellaity.com/2020/01/31/string.html
======
dylanmclark
Reminds me of a talk a few years ago about Facebook's internal implementation
of std::string. They do the same short string optimization, but Facebook
manages to outperform this implementation by storing 24 bytes (vs 23) in
"short string mode".
IIRC, Facebook achieves this by using the last byte as the flag byte. To
signify short string mode, this flag is set 0. This allows it to also serve as
the null terminator. Tricky!
~~~
fyp
It's a tradeoff. In libc++'s version you still have string size stored in the
top 7 bits so you just need a bitshift to get size. It sounds like fb's
implementation would require looping until null terminator to get the size.
~~~
roel_v
To save those who, like me, were going to comment 'that would violate the
standard because std::string::size is required to be O(1) complexity' a Google
- the standard recommends but doesn't require that.
~~~
epistasis
Facebook's implementation would still be constant time for short strings,
because there's a constant which bounds the runtime.
Though I hear that the definition of big-O notation has shifted a bit in
Silicon Valley these days so maybe that answer would get me in trouble in an
interview.
~~~
ryani
It's true that big-O notation only concerns behavior with large N, but it's a
bit disingenuous to say that the loop executes a constant number of times --
by that argument, you could say that if you implemented size() by strlen()
it's O(1) because the string must be less than 2^64 bytes long on a 64-bit
machine.
So I can see why someone would claim that implementing size() via strlen()
"only" for small strings shouldn't be considered O(1), because strlen() is
O(n) and within that class of strings the runtime is increasing as the length
increases.
~~~
coolplants
I think it’s a bit more disingenuous to compare the magnitudes of 2^64 and 23
for the sake of argument, as if 2^64 isn’t practically asymptotic.
------
RcouF1uZ4gsC
Note that this implementation has undefined behavior according to the standard
because union members are accessed that haven't been written to. The code that
tests whether it the string is long or short, accesses members of the union
unconditionally.
This is fine because std::string is provided by the standard library and the
standard library is allowed to do stuff normal libraries are not allowed to
do. This technique does work in practice, but it is technically undefined
behavior.
~~~
Inityx
> standard library is allowed to do stuff normal libraries are not allowed to
> do.
How does this work, given that it's still written in C++? Is there special
casing in the compiler to define the behavior?
~~~
aidenn0
It will only ever be compiled with clang, so as long as clang doesn't
implement this behavior in a way that will cause it to be incorrect, that's
fine.
If it were to be special-cased, it would probably require an attribute or a
pragma or something. While it's not unheard of for compilers to automatically
detect they are compiling the standard library, it's fairly rare.
~~~
bregma
libc++ is compiled by compilers other than clang. It's a completely invalid
assumption that it will only ever be compiled by clang, because it's never
only over been compiled by clang.
I say this as someone with a full time paid job supporting libc++ compiled by
another compiler for a commercial organization in a safety context.
~~~
aidenn0
Oh, that's good to know. If obscure C++ compiler X were to cause incorrect
behavior of this code, would it be easy to upstream the fix?
------
userbinator
_The short string mode uses the same 24 bytes to mean something completely
different._
...and the reason short strings are that length is precisely because a long
string needs that amount of space to store the pointer, capacity, and used
variables anyway. On a 32-bit system, the short string limit is lower by half.
Also, as optimised as this implementation is, I have yet to see a compiler
that's smart enough to do things like replace "dumb" uses of std::string with
essentially the equivalent of what a smart C programmer using pointers would
write (as the saying goes, "the fastest way to do something is to not do it at
all.") Ditto for the other data structures in the library. In other words,
optimising individual classes approaches a local minima.
~~~
zelly
And the smart assembly programmer laughs at the C programmer. There are a
couple dozen string-oriented x86 instructions that I've never seen a C or C++
compiler produce. You could easily get a 2x speedup on strings by hand writing
clever x86 with SSE. In fact I'm surprised no one has made an STL with lots of
inline assembly.
~~~
erik_seaberg
Most of what I know predates SSE; does that have a long track record of being
fast? I know REP MOVSB was originally fast, and then CPU vendors decided it
was rarely used and did it in (slower) microcode, and then architectural
changes made it fast again sometimes depending on alignment.
~~~
userbinator
REP MOVS is still a microcode loop, but it will copy entire cachelines
(usually 64 bytes) at once if it can. The fact that it is a tiny instruction
(2 bytes) and runs in microcode means that it doesn't consume instruction
fetch bandwidth while it's running, and occupies only a tiny amount of the
instruction cache.
------
kccqzy
Here's something that once bit me. The libc++ implementation uses short string
optimization. Which means no heap allocation for short strings. Unfortunately
I didn't know this and naively thought when you std::move a string, the data()
buffer would remain unchanged. This is then incorrect. You can manifest this
by storing strings into any container that moves their elements around like
std::vector or absl::flat_hash_map.
~~~
zvrba
> when you std::move a string, the data() buffer would remain unchanged
You cannot assume anything about the state of a moved-from object. AFAIK, the
only valid operations are destruction and assigning something else to it.
~~~
quietbritishjim
> You cannot assume anything about the state of a moved-from object.
This is the right default assuption, but classes are allowed to have (and
document) more specific behaviour. For example, it is guaranteed that
std::unique_ptr and std::shared_ptr are empty (nullptr) after they have been
moved from, and std::vector is guaranteed to be empty after it is moved from
so long as the destination allocator is the same.
> AFAIK, the only valid operations are destruction and assigning something
> else to it.
Even for classes whose move constructors have no guarantees, there are often
other methods that don't have any preconditions, such as calling clear() or
resize(0). In fact is it allowed to call other operations and they should
behave consistently, it's just not guaranteed what exact value the object
should have (e.g. if size() > 0 then .at(0) should not throw and a second call
to it should return the same value as the first call to it).
~~~
zvrba
You're right. But I've given up "language lawyering" a long time ago: I have a
set of "rules of thumb" (like the one I just wrote) that exclude some
technically valid programs, (but so be it) and that let me write robust code
quickly without spending time on digging through the documentation for special
cases.
Even if I did know every single edge case in the language and library, the
developers next to me might not. Then they decide to emulate me (many learn by
example) and catastrophe ensues.
------
yongjik
I always wondered why these string implementations have full 8 bytes for
length. Many programs use millions of strings (or more), while very few would
ever use a >2GB string. It would make sense to use, say, "not-too-long string
optimization" where you only store 4-byte lengths for any string <2GB, and use
the remaining one bit to mean "the length is in the data block".
But I guess these people have run the benchmarks. ...Or maybe not. I have to
wonder.
~~~
usefulcat
It could be done as you say, in 16 bytes (assuming 64 bit pointers):
struct not_too_long_string {
char* data;
uint32_t size;
uint32_t capacity;
};
Of course, if you do it that way then the longest string you can store with
the small string optimization is probably ~15 bytes instead of ~23. So
although you do save 1/3 on the size of each string, on average you're
probably still going to end up doing a greater number of dynamic allocations
because of the reduced small string capacity. Unless of course you know a
priori that a sufficiently large portion of your strings will be > 15 bytes
anyway, which of course the implementors of std::string almost certainly don't
know.
Edit: I failed to notice the part about the length being in the data block
(doh). I guess the disadvantage to putting the length there would be that an
extra indirection is required to get the length, a rather common operation.
And as others have pointed out, that only saves 4 bytes, which will be used
anyway for alignment..
~~~
jcranmer
If you want to get really fancy, you can do it in 8 bytes. Pointers are only
48-bits on 64-bits, so you can squeeze a 16-bit size field. If size overflows
that, then you can use a cookie before the data string to find the size.
Capacity could be stored in such a cookie, or junked entirely and you rely on
your memory allocator to get the size of the allocation (small-string
optimization obviously not even being considered in this model).
------
Thorrez
> I will assume that ... the char type is signed and 1 byte wide.
You don't really need to make an assumption about being 1 byte wide. That's
guaranteed by the standard.
[https://en.cppreference.com/w/cpp/language/sizeof](https://en.cppreference.com/w/cpp/language/sizeof)
~~~
stuffypages
Thanks! Fixed.
~~~
stuffypages
Interesting, the page you linked also says this.
>Depending on the computer architecture, a byte may consist of 8 or more bits,
the exact number being recorded in CHAR_BIT.
I'll add that as an assumption.
~~~
thedance
Does it make a difference? It doesn't seem like your article relies on
CHAR_BIT being 8.
------
huhtenberg
In situations when there might be a lot of _empty_ strings, the 'capacity' and
'size' can be taken out of the fixed part and bundled with the data instead.
This will bring sizeof(string) to a size of a single pointer and will still
allow for short strings of 7 chars (in 64-bit builds).
Memory allocations are usually aligned by default, so the pointers will have
at least one lower bit cleared and available to be used as a mode flag.
If in doubt, allocating through aligned_alloc(2,...) will guarantee an unused
bit in a pointer.
~~~
gpderetta
Yes, sometimes it is worth to optimize for size, especially if the string is
actually not used in any fast path and just need to be there.
I'll mention though that std::string (well, basic_string) takes an allocator
parameter, so it could only enable this optimization for 'well known'
allocators that provide aligned buffers.
------
amelius
Isn't the __cap__ field available also inside the malloc block header, so
couldn't this field be optimized out of the std::string implementation?
~~~
thedance
No. You can’t make assumptions about how global operator new works. Allocators
like tcmalloc are allowed to override it. And string can be instantiated with
any stl allocator, so it might never call ::new anyway.
------
jnordwick
Does anybody know why vector isn't allowed short buffer optimization or if it
will be changed in the future?
~~~
gpderetta
You could say that while most string are small, vectors are all kind of sizes
and the T size itself can be large, so the optimization is less of a win in
for a general purpose container.
But it is mostly for historical reasons. I believe the original STL used the
SSO optimiziation [1], so there was never any assumption about the stability
of references to string elements, while there is a lot of code that assumes
that references to vector elements do not change.
[1] The SGI STL, direclty derived from the original HP STL had extensive
rationale on why it didn't implement COW; libstdc++, which I believe also
traces its roots from it, decided to instead do COW. The rest is history.
------
lallysingh
Typo in title. That's std::string.
~~~
stuffypages
Thanks! I don't think I can edit it now though :(
Does the edit button disappear after a certain amount of time?
~~~
thenewnewguy
I don't believe you can ever edit the title of a submission, but the mods can
(and typically will).
| {
"pile_set_name": "HackerNews"
} |
Ask HN: US Federal Deficit - What to do? - mdink
So while driving this morning, I had NPR on listening to US lawmakers give the typical run around about spending cuts. It seems like we are coming close to a dangerous stand still, which would obviously have dire consequences for the future of the US.<p>How come both sides can't seem to realize that when it comes to spending cuts EVERYTHING needs to get cut and unfortunately taxes need to be RAISED. No one wants to hear this - heck I don't want to pay more taxes. I also don't want to see gov agencies doing great things be cut severely, but the fact of the matter is that 14 trillion isn't going to go away quietly.<p>Now regardless of whether you think I am right or wrong in this assessment, I have continuously been impressed by the massive brain power behind HN and I am curious to hear people's thoughts on what needs to be done and why. If you are an international reader, feel free to share your outside perspective!
======
gtlenz
The interactive map doesn't allow one to account for increased economic
growth. That's the argument behind supply side economics. There are two books
that best lay out an approach to fix the budget deficit by cutting taxes. I
know this sounds crazy, but I encourage everyone to give them a read. I've
also included JFK's speech to the New York Economic Club (He'd be with
Republicans today on fiscal issues). Even if you read them as a mental
exercise, it will help you understand why Republicans advocate cutting taxes:
JFK's address to the New York Economic
Club:[http://www.americanrhetoric.com/speeches/jfkeconomicclubaddr...](http://www.americanrhetoric.com/speeches/jfkeconomicclubaddress.html)
Econoclasts by Brian Domitrovic: (This book shows why when Bush 43 cut taxes
it didn't lead to growth. Mundell's policy mix is key)
[http://www.amazon.com/Econoclasts-Supply-Side-Revolution-
Pro...](http://www.amazon.com/Econoclasts-Supply-Side-Revolution-Prosperity-
Enterprise/dp/193519125X/ref=sr_1_1?ie=UTF8&qid=1298048013&sr=8-1)
The Growth Experiment by Lawrence Lindsey [http://www.amazon.com/Growth-
Experiment-Policy-Transforming-...](http://www.amazon.com/Growth-Experiment-
Policy-Transforming-
Economy/dp/0465027512/ref=sr_1_1?s=books&ie=UTF8&qid=1298048203&sr=1-1)
I don't disagree that spending is the main culprit of the budget deficit, but
there is a way out of our predicament that few if any are talking about.
Historically tax revenue is equal to about 18% of GDP. So in order to have a
balanced budget at 3.73 trillion we would need a GDP of 20.7 trillion . To
balance our budget, assuming no growth in spending, it would take 7 years of
5% growth. It would take 5 years at 7% growth and if we could get to 8%
growth, agreed to keep the budget at 3.73 trillion, in year five we could pay
300 billion of our national debt down. In my opinion, growth is literally the
only way out of our problem without devaluing our currency. The tax raises
necessary to fix our problem would choke off our ability to grow.
~~~
curt
Even though its counter intuitive tax cuts work, but they have to be the right
kind. All these credits, temporary cuts, refunds don't do anything. Its the
flat rate lowering and tax simplifications that increase growth and revenue
because it alters long term behavior. A great recent example is Egypt, they
lowered their rate from 40% to 20% and doubled revenue while standard
forecasting said it would be cut in half. Other example are abound throughout
the former Soviet Bloc, you lower/simplify taxes you get more revenue.
In the US we spend more money complying and avoiding taxes then actually do on
the taxes themselves. Think about that. If you look at US government tax
revenue it's always about 18% of GDP no matter the tax rate. (Look it up, its
really interesting it's called Hauser's Law) So the only way the increase
revenue is to grow the economy and the highest correlation to economic growth
is how many billion dollar companies an economy produces each year. So
everything the government does should be centered around freeing start-ups to
become billion dollar companies. That means simplified regulation and the
removal of corporate welfare, both protect large companies from smaller start-
ups.
------
schwabacher
The new york times had a really cool flash app that let you balance the
budget..
[http://www.nytimes.com/interactive/2010/11/13/weekinreview/d...](http://www.nytimes.com/interactive/2010/11/13/weekinreview/deficits-
graphic.html)
Here is how I did it:
[http://www.nytimes.com/interactive/2010/11/13/weekinreview/d...](http://www.nytimes.com/interactive/2010/11/13/weekinreview/deficits-
graphic.html?choices=wvxj35rc)
It isn't easy, but getting out of Iraq and Afghanistan and letting the Bush
tax cuts expire go a long way.
~~~
bhousel
Can't upvote this enough.. Back when this came out, I shared the link on
Facebook. It was interesting because I know a whole spectrum of very liberal
to very conservative people among my family and friends.
This exercise really opened a lot of eyes, and I saw people with very strong
political views start to change their minds about long standing beliefs. In
order to fix the deficit, we will need to put politics aside and accept the
best ideas from both sides.
------
jhamburger
-Drastically cut defense spending (The cold war is over. We aren't getting into any dogfights or naval battles. Concentrate spending on urban/guerrila warfare.) -Reform social security and medicare -Cut where you can elsewhere
~~~
mdink
Curious - Do you agree with 500 million for cyber security?
------
turbojerry
Raise taxes, quickens deflationary collapse
Cut spending, quickens deflationary collapse
Print money (QE), hyperinflationary collapse
"Now, America's just another broke ex-super power looking for a handout and
wondering why." - Max, Dark Angel
------
pzxc
If we only reduced spending to what it was in the year 2000, we could
completely eliminate the income tax. That's how much spending has increased in
the last decade.
------
mdink
Update: Also I am curious to thoughts specifically on the $500 million for
cyber security. Too much? Too little?
~~~
kongqiu
We should probably be spending more on cyber-security than for, say, making
sure our fighter jets are 3x better than anyone else's...
| {
"pile_set_name": "HackerNews"
} |
NASA, Saylor Foundation to Offer New Free Space Systems Engineering Course - cryptoz
http://www.nasa.gov/press/goddard/2014/february/nasa-saylor-foundation-collaborate-to-offer-new-free-space-systems-engineering/#.UvOVsUJdVb5
======
rch
Since this is affiliated with a government agency and aimed at the general
public, my main concern is that the material will be completely insubstantial.
------
gemma
Not a MOOC, but the Stevens Institute of Technology offers an (online)
accredited graduate degree program on the same topic:
[http://www.webcampus.stevens.edu/Space-Systems-
Masters.aspx](http://www.webcampus.stevens.edu/Space-Systems-Masters.aspx)
------
JoeAltmaier
Why are they always 'Massive'? What if only 4 people sign up? Then is it a
TOOC?
~~~
philjones
“Fool of a TOOC!" he growled. "This is a serious journey, not a hobbit
walking-party."
------
blueblob
Does anybody know if they are going to archive the content like
opencourseware? It would be nice to be able to follow at your own pace.
~~~
my_username_is_
yes, Saylor's mission is to create and/or locate OCW equivalencies for an
entire degree. You can see what's currently available at Saylor.org
------
iambateman
Thus society finally finds out whether the phrase "It's not rocket science"
actually has any merit.
~~~
pirateking
I remember John Carmack saying something along the lines of game engine
development being harder than rocket science.
| {
"pile_set_name": "HackerNews"
} |
DTACK GROUNDED Archive - comatose_kid
http://www.easy68k.com/paulrsm/dg/
======
comatose_kid
Anyone who has ever hacked 68000 ASM or h/w should check out this cool
newsletter from the early/mid 80s.
| {
"pile_set_name": "HackerNews"
} |
Dutch security chief says Russia is trying to hack government websites - vschwaberow
http://www.dutchnews.nl/news/archives/2017/02/dutch-security-chief-says-russia-is-trying-to-hack-government-websites/
======
tdkl
You forgot to mention China and Iran, but I understand click bait is important
nowadays.
| {
"pile_set_name": "HackerNews"
} |
House costs just $20,000 but its nicer than yours - gamechangr
https://www.fastcompany.com/3056129/this-house-costs-just-20000-but-its-nicer-than-yours
======
nostrademons
In hot metro areas the problem isn't the construction costs, it's the land. A
1/4 acre tear-down in Cupertino or Sunnyvale goes for a million dollars; an
empty half acre goes for two million.
It's hard to fix this: the root problem is that _income_ is concentrated in a
small number of areas that are constrained by geography, not that houses are
expensive to build. In areas with plenty of land around well-dispersed
businesses (eg. Houston or North Carolina), nice houses can be had for $200K.
In areas with no income (eg. Detroit) nice houses can be had for $10K, but you
wouldn't necessarily want to live there anyway.
~~~
gamechangr
very interesting...
Would you extend that observation to other areas : like Seattle?
Where outside of California would you invest as a future place that's likely
to increase like Mountain View (a have a few friends that live there that also
say "it's the land").
Thanks!
------
imtringued
It wouldn't surprise me if it will costs me an additional $3000 per year just
for the additional gas.
| {
"pile_set_name": "HackerNews"
} |
RaspBSD – FreeBSD images for the Raspberry Pi - fcambus
http://raspbsd.org
======
BrainInAJar
How does FreeBSD work with the GPIO pins, and also things like i2c ? I'd love
to not use Linux, but i use my Raspi as more than just a tiny computer
~~~
skreuzer
FreeBSD has full support for GPIO and i2c on both the RPi 1 and 2. Simple
wrappers around FreeBSD's GPIO ioctl can be found at
[https://github.com/gonzoua/freebsd-gpio](https://github.com/gonzoua/freebsd-
gpio)
~~~
jlarocco
I'm more curious if WiringPi is usable or ported over?
------
gregwtmtno
I put FreeBSD on my Raspberry Pi B a few months back. (Similar images were
previously published as well.)
I had to abandon the project, though, because there were very limited binary
ports and base-system updates available. Compiling things on the Pi is a pain
when possible at all. I did get a fairly decent cross-compile setup going, but
in the end, it was more trouble than it was worth.
~~~
josh64
I was pleased to see the following on this site:
> Currently work is ongoing to build and publish offical FreeBSD packages.
> Once those are published, these images will use them.
------
sigjuice
Why aren't such images available at the official location
[http://ftp.freebsd.org/pub/FreeBSD/snapshots/arm/](http://ftp.freebsd.org/pub/FreeBSD/snapshots/arm/)
(or a mirror) ?
~~~
Sanddancer
There are official images
[http://ftp.freebsd.org/pub/FreeBSD/snapshots/arm/armv6/ISO-I...](http://ftp.freebsd.org/pub/FreeBSD/snapshots/arm/armv6/ISO-
IMAGES/11.0/) . This project seems to be aiming to be the PC-BSD for arm-based
boards, with different defaults for people new to FreeBSD, etc.
------
mirimir
I would love to see pfSense (based on FreeBSD) on the Banana Pi. It has a real
gigabit NIC :)
------
eschaton
I thought the RPi 2 was armv7, why is the image for it using armv6?
Does BSD support fat/multi-architecture binaries?
~~~
jpablo
It's the same approach the official Linux Raspberry PI images follow that way
you can support all raspberry pi versions with a single images.
There potentially could be an speed up by rebuilding everything for armv7
(specially for NEON-fp) but no one has done it yet.
~~~
aerique
Any idea what kind of speedup one could expect?
~~~
feld
I don't know, but I would assume it's similar to setting CPUTYPE in your
make.conf so binaries are built with some cpu-specific asm for your specific
flavor of x86 CPU: you'll get a performance boost, but nothing mind-blowing.
------
tdicola
That's awesome, it's always great to have more choices of OS. Cool to see
they're looking at other boards like the BeagleBone Black too.
------
mvanotti
I've tried freeBSD in a Raspberry Pi 1, but I couldn't get any binaries
precompiled for ARM :(. I would like to have an easy way to cross-compile
ports from my main machine.
~~~
corv
Take a look here:
[http://blog.ignoranthack.me/?p=212](http://blog.ignoranthack.me/?p=212)
------
hibbelig
Is there something similar for the Cubietruck?
~~~
dijit
[https://wiki.freebsd.org/FreeBSD/arm/Cubieboard](https://wiki.freebsd.org/FreeBSD/arm/Cubieboard)
------
poseid
might be nice to have this freebsd on an intel edison too
| {
"pile_set_name": "HackerNews"
} |
Show HN: Sempl – Stupid Simple Bash Templating - nextrevision
https://github.com/nextrevision/sempl/
======
learning_still
If anyone uses this, please share. As a newb, I would love to see some real
use examples to learn from.
~~~
nextrevision
Sure thing, I'm currently using it in docker as a lightweight way to set
config files from environment variables. I'll put together a write up of
how/why we are doing that and post the link in reply to this.
~~~
nextrevision
Here's the write up. Let me know if there's anything unclear!
[http://nextrevision.github.io/2015/sempl-templating-with-
bas...](http://nextrevision.github.io/2015/sempl-templating-with-bash/)
~~~
learning_still
This is perfect! Thank you for taking the time to make this. It gave me a much
better understanding of what sempl is, how to use it, and what it can be used
for.
------
bashinator
How is this different from GNU envsubst (in the gettext package)?
~~~
nextrevision
envsubst will really just perform variable substitution, not perform any logic
or command substitution (e.g. $(hostname -f)). It's also limited, from what
I've seen, in support for other bash variable actions (such as defaults). You
can also write loops with output similar to other templating languages here as
well.
~~~
pdkl95
Traditionally, this would be a job for m4:
$ cat examples/config.yaml.in
user: USERNAME
password: ifelse(PASSWORD,`PASSWORD',`defaultpass',PASSWORD)
files:
patsubst(esyscmd(`ls'), `.+$', ` - \&')
$ m4 -DUSERNAME=somebody examples/config.yaml.in
user: somebody
password: defaultpass
files:
- README.m4
- examples
- sempl
| {
"pile_set_name": "HackerNews"
} |
Burglar targeting startups in San Francisco - qq66
He stole two laptops from us this morning in SOMA and looks to be part of a crime ring involved in other burglaries according to the police. Stay on the lookout and contact me ([email protected]) if you recognize him from other burglaries. $2,500 reward for conclusive information.<p>His MO is to be extremely well dressed and knock on the door first, and pry the door open with a screwdriver before opening the latch with a metal card.<p>http://makeagif.com/i/jZ8Ibg
======
paulsutter
In the early days of Quantcast we had a couple robberies in our second SOMA
office. Fortunately most people had taken their laptops home but we lost a few
things.
The police were apologetic, said that even if we had proof and knew who it was
the DA wouldn't press charges (this was 5 years ago, different DA, but I doubt
the caseload has changed). The officer said to basically consider stuff in our
office to be as secure as stuff left visible in a car when parked.
We asked the officer how the robber got in. His eyes lit up, he finally felt
useful. He took a quick look around and in two minutes showed us how the
robber had gotten in. We fixed that, and never had another breakin.
A useful lesson in how the police can actually help.
------
avichal
Can you share any more details?
Where in SoMa your office is located? Rough intersection should be ok.
What time did the robberies happen?
What ethnicity is he?
~~~
qq66
8am Tuesday near South Park. Black male age 35-45. Burglaries were at 8am on
Tuesday morning.
| {
"pile_set_name": "HackerNews"
} |
Xmpp.is needs donations to pay for their servers - jollyjester
https://xmpp.is/
======
dzek69
Well. Old-fashioned communication is dying anyway. Even IRC channels I used to
be active on even in 2017 are now moving to different platforms like Discord.
For person to person communication no one I know was using XMPP still uses it.
Is that good or bad? Probably bad. Single open and secure standard (I don't
care which one) should be better for average person experience. Not having to
keep 4 apps running and stuff.
~~~
phyzome
At this point, I only know a couple other people who use Jabber (I hate the
XMPP name). I think OMEMO (double-ratchet encryption like Signal uses) and the
Conversations client for Android (which supports a good "baseline" suite of
XEPs -- Jabber extensions) have a good shot at revitalizing it, though.
------
tibu
I never used Jabber / XMPP but now I'm think of setting up my own Matrix
server. Which one is it worth for everyday communication on the long term?
XMPP or Matrix?
------
jollyjester
:^)
| {
"pile_set_name": "HackerNews"
} |
Apply HN: Lenzy – affordable photographers guaranteed to suit you, booked in 50s - louisswiss
With Lenzy you can choose the perfect photographer for your needs, get a guaranteed price and book/pay within 50 seconds. Bookings will either take place via our web-app or, more commonly, our JS plugin embedded in third party websites and apps where users might need the services of a photographer (e.g. a job platform, shopify, airbnb, ebay etc). Instead of choosing a photographer based on their profile, our photo recommendation engine lets you choose the right photographer for your needs based on samples from their portfolios in a tinder-style interface.<p>As avid photographers ourselves, we know that this is the optimal way of finding the right photographer for your project, due to it being a much more subjective, individual perspective than other on demand services such as cleaning, transport etc, where safety and peer-approval are paramount (the photographer who my friend thought did a great job at her wedding, for example, is probably not the right person for my e-commerce product photos). Interestingly, thanks to the general increase of interest in photography and the improvement in photography hard- & software, 90% of the 'best' photographers out there are actually amateurs, art-students and other hobby-photographers who 'occasionally do shoots for friends'. By harnessing this eager supply, matching efficiently and increasing the demand by making awesome photos available to everybody at a price they can afford, we can offer a better quality experience than 'professional photographers' at less than half of the price.<p>We are a team of 3, who have worked together successfully on projects before...<p>- 1 designer & professional photographer
- 1 (mainly front-end) dev/amateur photographer/sales guy
- 1 back-end dev (not great at taking photos, but has seen thousands in his lifetime)<p>We have a working beta and partnerships with third party sites which are profitable.<p>We would love to field your questions/feedback :)
======
fitzwatermellow
Lots of nascent demand for pro photo services. Culture is becoming visual on
an unprecedented scale. Two quick queries:
1\. How quickly do you think you could scale this globally? Customer requests
a shoot on a volcano in Greenland for example ;)
2\. Why not provide a full service solution? That is not just the
photographer, but for a fashion brand shoot for example, all the models, hair,
makeup, location, catering, legal clearances and the other 100 things I am not
anticipating ;)
~~~
louisswiss
Thanks, we agree! Even more importantly, the definition of 'pro photo
services' is changing rapidly from _high prices, fixed retail location_ to
_high quality, style & subjective fit_.
1\. This would be awesome and hopefully we can manage it someday, however a
lot of stock photo websites actually cover this pretty well already (assuming
you just want custom photos of the volcano). In our experience, if you can
afford to actually have your event/wedding/CV-headshots (now that would be an
awesome LinkedIn profile photo) taken on location in Greenland, you tend to
find shipping out your 'usual' photographer with you and putting them up in a
hotel as a negligible cost ;)
2\. This could be something we expand to later, but we want to focus on what
we know and do best now and make it a really great service. Also, our JS
plugin means we partner with companies already offering some of these services
to generate free new bookings, so we don't want to alienate anybody :)
~~~
louisswiss
Forgot to add that in a lot of cases (especially fashion shoots), there is
more equipment needed (lighting, reflectors etc) and normally a second person
is needed to 'handle' this equipment during the shoot.
We are working with our photographers to give every one of them access to this
service/equipment and normally one of the models will help out as the second
person, keeping costs low.
------
kumarski
In this business, the proof is in the results.
I imagine many YC folks have seen these types of companies before.
I can name 2 in my head, but they don't do the tinder style interface.
eversnapapp.com PrettyInstant.com
Godspeed. I think you're on to something.
~~~
louisswiss
Thanks for the inputs - I agree, there must be 100s of similar applications
each year relating to on demand photography.
We love the concept of eversnap, however it is a bit of a risk leaving your
wedding day/event in the hands of (possibly inebriated) guests :)
I think our target market is less events/weddings and more the other areas of
personal and professional life where great photos can make a BIG difference,
but price and time constraints (for finding the right photographer)discourage
people from using traditional services (like PrettyInstant). Examples would be
when renting out your home, selling something online, photos for the marketing
department (headshots, teamphotos, e-commerce product photos, CV-style photos
etc.
We love the tinder interface and it seems to work well, but at the end of the
day it won't put us head and shoulders above the competition. What really sets
us apart is that with us, you book a photographer by judging how they shot a
photo which had similar requirements to your shooting. It seems crazy to us as
photographers that PrettyInstant (for example) guarantees to only work with
'the best' photographers, yet depending on what style you are looking for, the
lighting and the general setting (is it a headshot or documenting a party?),
any one photographer could be the perfect fit for you or they could be
terrible.
~~~
scotu
disclosure: I work on eversnap
eversnapapp.com was never meant to replace pro photography wedding photos, but
to add some authenticity to the mix (and capturing any friends and family get
together), plus we offer live slideshow moderation ;)
We also complete the offer with our own professional photography service on
eversnappro.com
That said, best of luck to you and your team!
~~~
louisswiss
nice - I hadn't looked at eversnappro.com before.
I wasn't trying to insinuate that eversnapapp.com was trying to replace pro
photos - I love the idea, the execution and would definitely use it myself ;)
------
pjlegato
What is your marketing plan to reach both the customers and the photographers
who will use the app?
~~~
louisswiss
Ah, the classic chicken & egg problem ;)
Finding awesome photographers has been much easier than we expected - by
posting 'photographer needed' adverts on forums/in camera shops/in facebook
groups it is easy to get a few hundred responses within a week. Over 50% then
sign up because there is no fee or obligation and hey, why wouldn't you?
We don't have the website live in an open beta yet, so we don't know how much
the b2c marketing will cost - we are actually focussed heavily on working with
partner websites to get them to embed our JS booking widget into their
websites. We are trialling with a job-platform and it is a great way for us to
reach customers at exactly the 'right moment' (ie when they have the need for
a photographer but perhaps hadn't fully considered it). The partner website
then gets a commission from each booking, so it is a great additional revenue
incentive for them as well.
So far, our customers have been really happy and word of mouth seems to work
really well for getting new bookings - this was really important for us as we
weren't sure that the customers would refer their friends to us at Lenzy and
not just to the photographer they worked with directly. By giving our
photographers a small commission on bookings we receive from their customers'
referrals, we seem to have avoided the HomeJoy problem (for now).
| {
"pile_set_name": "HackerNews"
} |
Why Do We Need to Sleep? - nature24
https://www.theatlantic.com/science/archive/2018/01/the-mystery-of-sleep-pressure/549473/?single_page=true
======
krausejj
[https://www.amazon.com/Why-We-Sleep-Unlocking-
Dreams/dp/1501...](https://www.amazon.com/Why-We-Sleep-Unlocking-
Dreams/dp/1501144316) is a fantastic new book on the subject, if you're
interested in going deeper
| {
"pile_set_name": "HackerNews"
} |
The Unofficial HN FAQ - jacquesm
http://www.jacquesmattheij.com/The+Unofficial+HN+FAQ
======
pchristensen
Another good one:
Q: Why don't people ever email me when I invite them to in a comment?
A: The Email field in your profile is for site administrators only. If you
want other users to be able to see it, you need to include it in your About
box.
~~~
jacquesm
Ok, added.
------
po
_A high average score on your comments will give your comments preference in
the search order (this is part of the 'secret sauce')._
I've wondered about that… I spend a fair amount of time reading through the
"newest" and "ask" lists and often comment on articles that don't end up
making the front page. This can really drag your average down. The best way to
have a high average score is to comment only on top stories where everyone
else is reading, which I think is a bit unfortunate.
~~~
jacquesm
Yes, I fully agree. I remarked as much to PG that this would be an unintended
and negative side effect when he implemented this, but I don't care one bit
about my 'average karma' so that's just too bad, and I'll keep on answering 1
upvote 'Ask HN' posts anyway.
~~~
frossie
The thing that makes me a bit sad is that is that some people do try and be
helpful and respond to Ask HNs that are languishing unresponded... and yet
only have one point of karma on their comment.
Which means that even the person who asked the question didn't upvote the
commenter who was taking the time to respond to them. I've seen this even in
cases where the OP followed up on the comment and said "thanks that's very
useful". So click the up-arrow, dude.
(unless upvotes by the OP are filtered out? but I can't imagine why that would
be)
~~~
qeorge
_(unless upvotes by the OP are filtered out? but I can't imagine why that
would be)_
AFAIK they are. For instance, if I were to upvote your comment it would have
no effect.
This definitely happens if you comment and then upvote. Not sure about the
reverse order.
------
telemachos
I'm not sure how big of a deal this is, but it might be worth mentioning that
many HN users dislike short URLs and will often vote you down if you post one.
Just a community norm that some folks are surprised by.
~~~
RK
And HN currently has no way to remedy accidental down (or up) voting, which is
particularly problematic on touch screens.
------
j_baker
"Simply flag the post, don't bother bitching about it, that will only get you
downvotes."
This isn't _always_ true. I've bitched about submissions and gotten upvoted
for it. :-)
Usually, it's something along the lines of "I'm tired of seeing this crap on
the front page" though. Usually if it's "this is _hacker_ news" or "N00b, this
is a violation of the rules" it will get downvoted.
One other point to make, it's ok to point out that someone is breaking the
rules if you're not _bitching_ about it. I think comments saying "You might
not realize this, but this will likely get downvoted/flagged because it breaks
rule X" comments should be encouraged.
~~~
ugh
I sometimes like to explain exactly why I don't think something should be on
HN (if it's not spam or of really bad quality) - simple one liners like "This
shouldn't be on HN, flagged." aren't helpful at all. Be constructive!
I think feedback helps at least some submitters tremendously.
------
revorad
Great list. You might want to edit the title to replace "HN" with the full
form "Hacker News".
Another noob FAQ is: "Is HN becoming like Reddit and Digg?". pg has given lots
of good answers to that (mainly that people who haven't been around long
enough see patterns in randomness).
Edited to add: You might also want to point out that Reddit and Digg are also
good communities with a different feel, and there is no need to take a moral
high ground.
~~~
jacquesm
Title changed.
I don't see how I could have missed the reddit/digg one, I've added it.
------
mcknz
"Is there an API for HN / is it ok to scrape HN?"
Comment from PG: <http://news.ycombinator.com/item?id=1721105>
~~~
jacquesm
Thank you, added that.
------
warwick
A couple of things you might want to include:
The rule about having to be here for a year before you can even talk about if
we're turning into Reddit. It's in the guidelines, but I think it's worth
mentioning under "Is HN becoming like Reddit and Digg?".
It's also pretty courteous around here to note any edits you made to your
comment with a brief footnote, or by adding the additional content as a
footnote itself. The footnote should mention what was edited, not just that
the edit occurred. That bit of etiquette might fit under "Someone edited a
comment I replied to and now I look like an idiot!"
------
tptacek
Does anyone seriously believe that your chances of getting into YC go up
linearly with your karma? If I had to guess, past a certain threshold, your
chances of acceptance probably drop.
~~~
SkyMarshal
I suspect pg is looking for certain traits in your comments - maturity,
technical knowledge and/or experience, and some insightfulness into your
field. "Thoughtful" can comprise all three, and more.
If you have high karma, but most of your comments are noise, that can't help.
Or if you have low karma and rarely post, but your posts are mostly
"thoughtful", that probably helps.
I suspect it varies like that.
~~~
lotharbot
pg has stated that YCombinator is looking for good/great people, even if their
startup idea is weak. He's also stated that skimming your HN comments provides
one way to judge what sort of person you are.
Most high-karma people on HN (like, 5k+) get there by being thoughtful. I'd
imagine pretty much everyone in the top 100 would be helped rather than hurt
by their HN presence. I suppose it's theoretically possible to amass a lot of
karma without making any useful contributions, but I haven't see anybody do it
yet.
------
tnorthcutt
"The thresholds at which this happens changes over time, I believe the
downvote cap is at 50 right now and the flag cap is at 200."
I may be reading this wrong, but I think what you're saying is that once you
reach a karma of 50, you can downvote comments. I'm pretty sure that's
incorrect - I have a karma of 89 as of this writing, and (unless I haven't yet
figured out how to) am unable to downvote comments. Maybe someone who recently
became able to could give a more accurate number.
~~~
jeebusroxors
I'm at 147 and no down vote. I think he has it backwards? I had heard
somewhere else 200 was the magic number for comments.
~~~
jessor
Yes, you need a karma of 200+ to be able to downvote. Reached that just a few
weeks ago. You can only downvote comments which were made after you reached
the treshhold.
~~~
icey
Only partially true - nobody can downvote comments after a certain amount of
time. I'm not sure if it's 12 or 24 hours; but it's a fairly short window.
~~~
jacquesm
24 hours.
edit: proof: <http://pics.ww.com/d/425306-1/downvote-cutoff.png>
That's the 'comments' list.
~~~
jessor
Ah. Thanks for pointing that out.
------
devmonk
'"self" posts, posts that do not link to another website have their own
category in the top menu bar, they are all grouped under the 'Ask' entry...'
But that doesn't happen for every "Ask HN" I've posted. A good number move
there, but not all, and not immediately.
~~~
tsycho
I faced the same problem. Since I couldn't find the "Ask HN" rule clearly
mentioned anywhere, I even tried prefixing "Ask HN" in my post subject
speculating that maybe HN does a string search, but it didn't work.
Is there a minimum karma level for Ask HN posts? Or is this a bug in the
system?
~~~
jacquesm
Which post was that?
~~~
tsycho
<http://news.ycombinator.com/item?id=1747909>
~~~
jacquesm
It's there on the third page, currently entry #70.
~~~
tsycho
Thanks, not sure why I couldn't find it on the day I posted.
------
DanielBMarkham
This is a great article, Jacques.
Somebody should put together a list of meta-HN posts. These guides written by
the users have as much or more value than that the stuff pg and the rest put
together. I think part of the reason why is that fellow users are more likely
to see things from a user's point of view.
------
anonymous236
> _Why can't I respond to a comment that responded to me ?_
Current answer is wrong. Commenting is disabled for old threads. For new,
overly active threads only in-thread commenting is disabled, but clicking on
the 'link' link still gives an access to the response form.
~~~
RiderOfGiraffes
The answer is correct, but is (perhaps deliberately) incomplete. Replying to
recent comments is not disabled, there is an exponentially increasing timeout.
Yes, you can always click on the "link" link and then hit "reply", but in-
thread, the "reply" link only appears after a timeout that gets longer as the
comments get deeper.
In summary:
\+ "reply" on comments in old threads are disabled.
\+ "reply" on comments in new threads have a timeout
\+ the timeout is very short if the comment is shallow
\+ the timeout gets longer as the thread gets deeper
\+ the timeout can be circumvented by clicking "link" - then you are offered a
"reply" link immediately.
\+ PG might put the timeout out the shortcut method, but hasn't yet done so.
~~~
chmike
Do you mean a delay for the reply link to show up ? Timeout is confusing. I
didn't know about this feature.
------
gojomo
A nice summary, but I think a little too casual in recommending 'flags'. The
official guidelines mention flags for "spam and offtopic"; this FAQ says to
flag when you "think it's not HN material", a looser standard.
How about on-topic but trivial, repetitive, frivolous, flimsily-argued,
outside-the-mainstream, etc.? Best to _ignore_ , rather than _flag_ these -- a
flag is not a downvote saying 'less attention', it's a judgment ' _no_
attention; against-the-rules'. (It stings far more when your earnestly-offered
submission is killed than when it simply never musters many votes.)
I've noticed more people using flags as simple downvotes, and some good
submissions have been killed as a result.
~~~
jacquesm
That's true, let me think about that, that's a thing that will impact quite a
few entries actually.
If you want to re-word a specific entry in it's entirety I'd be grateful, this
is a hard one to get right.
------
RiderOfGiraffes
You might want to add a question:
\+ Why can't I downvote comment?
with the answer
\+ You can only downvote comments once you have sufficient karma. The required
level rises over time to account for the karma inflation caused by an
increasing userbase.
This would enhance the answer about what one can do with one's karma.
~~~
jacquesm
Ok, thank you! I've added the question and the answer + a bit to it about the
ability to downvote comments that are in reply to your own.
------
yurifury
You may want to add a section on alternative or mobile interfaces to HN, such
as hckrnews.com and icombinator.net.
~~~
jacquesm
Ok, done that. If there are others please let me know and I'll add them.
thanks!
~~~
nuclear_eclipse
HN Droid is an excellent app on the Market for Android phones that even allows
you to login, upvote, and post comments. It's even open source itself:
<http://github.com/amir/HNdroid>
~~~
jacquesm
Ok, it's added. thanks!
------
icey
This is a pretty good list, thanks for putting it together. Definitely going
to have to bookmark it for the times when new people complain about the way of
the world here.
------
bambax
Great post, thanks.
Typos:
_For one HN has it's own 'flavor'_ => its
_HN gets it's (more than) fair share of spam_ => its
Weird HTML:
It seems line-breaks are hard-coded with BRs inside of P elements? In this
phrase the BRs are missing and therefore it crosses over to the invisible
right side:
_The thresholds at which this happens changes over time, the downvote
threshold is at 200 right now and the flag cap is at 100. There_
~~~
jacquesm
fixed.
------
gasull
In the digest question you might want to add the RSS feeds from "A cure for
Hacker News overload":
[http://jmillerinc.com/2010/07/23/a-cure-for-hacker-news-
over...](http://jmillerinc.com/2010/07/23/a-cure-for-hacker-news-overload/)
------
edanm
Great list jacquesm. I had no idea Hacker News was open source! I guess you
learn something new every day.
And thanks for mentioning Resourcey. I've added your FAQ to HN's Resourcey.com
page (gotta love circular recursion!)
------
jacquesm
Update: I've added the possibility to link directly to an entry in the FAQ.
------
duck
One other search tip - I use Duck Duck Go's bang command to search HN using
!hn <search terms>. It takes you to searchyc.com, but is more handy if you are
already using DDG.
------
drtse4
The "Can I post links to my own blog ?", could not be true anymore, or at
least reading the ShelfLuv creator's post
<http://news.ycombinator.com/item?id=1754584> this morning i got that
impression (didn't we discuss this in a thread last week?).
~~~
steveklabnik
That shouldn't be true; his domain is probably autodead for a different
reason. This own post is submitted from jacquesm's own blog!
~~~
drtse4
I guess you are both right, but considering there seems not to be other links
to his blog on HN it still seems a bit weird.
------
rwmj
The FAQ is seemingly contradictory on the subject of downvotes. Does anyone
ever seen downvotes on posts? On comments? (I have never seen a "down" button
on either). The FAQ says that there are no such things, but also mentions
downvotes, which I find confusing.
~~~
stingraycharles
From the article:
"At what karma level can I downvote articles ?
There is no karma level that I know of that will allow you to downvote
articles."
and
"What [karma] does give you is that at some point you can downvote other
comments and it gives you the ability to flag posts."
In other words, you can't downvote articles, ever, and you can downvote
comments after a certain karma threshold has been reached.
------
stjarnljuset
Edit: nevermind, the thing I suggested adding was already on the FAQ.
------
chmike
An information I failed to find is text formatting methods. Sometime I see
itallic text, others courrier text. URLs aren't always shown as clickable
links. How can we control this ?
~~~
nitrogen
<http://news.ycombinator.com/formatdoc> (linked next to the about box on your
account settings page)
A Google search for "link:<http://news.ycombinator.com/formatdoc>
site:news.ycombinator.com" shows that others have requested more links to the
formatting help.
------
patrickk
Regarding "What can I do with my karma?" another thing you can do once you
reach a certain karma level is to setup a poll, with multiple answers that
people can vote on.
~~~
jacquesm
Ah yes, that's true there is a karma threshold for that too, I'll add that
right away. Thanks!
------
jacquesm
I just added this as a stand-alone article:
<http://news.ycombinator.com/item?id=1759548>
How to make the homepage.
------
bryanlarsen
Under "alternative ways to read", you're missing some punctuation. Currently,
it seems to imply that hckrnews.com is an Android app...
~~~
jacquesm
I re-organized that section to remove the ambiguity, thank you for the
pointer.
------
mortuus
typo: "otherwise you nobody can see it"
Where did you get the (one boat cruise|two boat race) saying?
~~~
jacquesm
Thank you, fixed the typo.
> Where did you get the (one boat cruise|two boat race) saying?
Long ago I designed a CAD/CAM system for a sailmaker in the Netherlands, the
effect of this is that I spent a ton of time in and around the sailmakery
itself (I even spent some time living in the attic above it because I had no
house) and the sailing related proverbs flew fast and thick there.
It's really true though, if you're on a boat and having a good time sailing
and someone overtakes you the urge to give chase is almost too strong to
resist, it's like having a hound spot a deer that is running away.
------
MarkBook
"Why would you want high karma ?" because I don't have one. Hit me
| {
"pile_set_name": "HackerNews"
} |
Ask HN: Have you ever “lost” a clever bit of code you weren't able to reproduce? - jarcane
Discussing with a friend on Twitter I was reminded that as a lad I once wrote an AI routine for haggling with a shop owner in an RPG that remains probably the best implementation I've seen.<p>Unfortunately, my brother then proceeded to power-cycle the drive with the disk still in, corrupting the file ... I was never able to reproduce the code because I couldn't remember exactly how I'd done it once I saved it.<p>Have you ever done something like this?
======
mchannon
Often I've lost code not permanently but came across it months or years later
after I thought I'd lost it.
More often than not, it turned out that the code wasn't clever so much as I
had remembered it being clever. The code itself often didn't even do what I
thought it had.
------
pjungwir
When I was a kid I wrote an ascii-art dungeon exploration game in BASIC on our
Tandy 1000. I worked on it for months, maybe even a couple years, adding and
adding. One day the floppy it was on failed.
I actually did rewrite it, and I remember noticing how much better the code
was. I didn't have to think about game design at all, just about the code. In
fact it was around that time that I finally understood what GOSUB was for. I
wouldn't be surprised if it was that rewrite that brought the realization.
------
rprospero
Not as much clever as infuriating, but I once had a bit of C++ code that would
run perfectly fine, unless you deleted one of the comments, at which point it
wouldn't compile. I lost the file in a hard drive failure many moon ago.
Mostly, I wish that I still had it simply to prove that the compiler really
was that buggy.
------
yen223
I once wrote an AI that solves the Sliding Block puzzle:
[https://itunes.apple.com/en/app/unblock-me-
free/id315019111?...](https://itunes.apple.com/en/app/unblock-me-
free/id315019111?mt=8)
The code is still in my PC, but I moved overseas, and didn't bring my PC
along.
------
divs1210
Once, when I was pretty much a noob, wrote a language called OOJASIC which I
implemented in Java. It was loosely typed, compiled to Java. I wrote a wrapper
over swing as its UI library, and a simplistic visual IDE along the lines of
BlueJ, that would show a smiling dino face if the file was compiled, and an
anxious one if it wasn't.
All that's left of all this is the compiler code (decompiled using cavaj), and
screenshots of the IDE (that I called Rex).
It was the most complicated piece of software I'd written at that point of
time, and there's little left to show for it.
Here's a link to the project page, btw. And don't judge. This is from a long,
long time ago.
[http://justaddhotwater.webs.com/oojasic.htm](http://justaddhotwater.webs.com/oojasic.htm)
~~~
divs1210
I would totally be able to reproduce it though, so it kind of misses the
point. I wouldn't be as dedicated probably.
------
informatimago
It happens. Usually, rewriting the code from scratch will produce a better
version.
------
andersthue
I once (while in university) had the awesome idea to write some fantastic code
after a night out.
Sadly I had to scrap the project the next day since it did'nt compile anymore
:)
~~~
jarcane
My father was the defacto Excel developer in his office and used to have vivid
dreams that consisted solely of him writing out the code for some problem he'd
been working on.
Then he'd wake up and forget the lot.
~~~
mc_hammer
this. the trick is when u cant remember to stop there, and dont worry or force
it, about 10 mins later the answer will come to u.
~~~
griff122
sadly, i use this same technique on the toilet.
| {
"pile_set_name": "HackerNews"
} |
Start-ups? We need more finish-ups - chrisbroadfoot
http://dondodge.typepad.com/the_next_big_thing/2011/03/start-ups-we-need-more-finish-ups.html
======
alexjawad
As an "experienced startuper" I strongly agree. Then again, the more
experience that is gained from failed startups will hopefully end up with more
finish-ups in the end so the result should still be positive.
| {
"pile_set_name": "HackerNews"
} |
Ask HN: As a guy with a PhD degree what are the opportunities to self funded? - notomorrow
======
WheelsAtLarge
I don't have an answer for you but I recommend that you pick an area you are
interested in and develop a bootstrap business there. Once you understand your
opportunities then you can get a better view of what you need to move forward.
You need to crawl before you run.
The advantage you have is that you are not afraid to learn. Reading relevant
books and dedication is what will move you forward. Also, make sure you don't
try to do it all yourself, strengthen your weaknesses. You're smart but no one
knows everything. Hubris will always be your downfall.
~~~
airbreather
I am always interested in the "strengthen your weaknesses" argument,
especially in light of "don't try and do it all your self".
Why wouldn't you understand your weaknesses just enough to know when you need
to get help and then focus on maximising your strengths?
You could reasonably suppose your strengths are what they are because of some
innate quality you possess, so the chance to be your very best is to build on
this.
| {
"pile_set_name": "HackerNews"
} |
Ask HN: What are the best Android forums or communities? - hollaur
======
sideproject
Reddit Android is a good one.
[https://www.reddit.com/r/Android/](https://www.reddit.com/r/Android/)
You can always start your own of course, if you are interested -
[http://www.hellobox.co](http://www.hellobox.co)
| {
"pile_set_name": "HackerNews"
} |
Ask HN: How did you get your first freelance client? - siquick
======
blackflame7000
The first freelance client I ever had was a company that one of my friends
worked for. It was a pharmaceutical company that was storing all their records
in large 3 ring binders. I told my friend that their records could be
digitized and stored on a central database and be accessible on all their lab
computers. My friend liked the idea and asked if I could put together a simple
proof of concept web service.
From there she demoed the prototype to her boss who loved it. She gave her
boss my email and we began discussing features, scope and price. After a
single in-person meeting we agreed to a features set, price, and delivery
date. 2 months later I delivered a product. There were some minor changes that
they requested after seeing the first version. I agreed to make the changed
and brought back a final version. Finally after the system was up and running,
I was paid.
I never really went looking for the freelancing opportunity, it just sort of
fell in my lap. I guess the main take away is always be on the lookout for
business inefficiencies that can be greatly improved by the skill set you
possess and then make an offer and see what happens.
------
doozy
From craigslist, and I ended up working like a week to earn $100.
But it got me started.
| {
"pile_set_name": "HackerNews"
} |
Paper Is Good...(paper industry spreading FUD about reading online?) - tomh
http://www.thehealthcareblog.com/the_health_care_blog/2010/11/paper-is-good-pass-it-on.html
======
daeken
One thing I think this article ignores is that there's a specific tipping
point at which it makes sense for a given publisher to drop paper, much like
there's one for when they should adopt digital in the first place. We've seen
the latter for most publishers, but we haven't yet seen the former for many at
all. It'll be different for every publisher, with certain things (e.g. tech
books) coming earlier than others, but it definitely exists. It'll be
interesting to see where it is for different publishers, and what ends up
remaining paper for a long time to come.
Another thing I just considered on the same subject: despite that the tipping
point is different for each publisher, if half the publishers in the world
have killed paper printing, it'll likely accelerate the other half to do the
same due to the lack of economies of scale; despite that demand is down,
production costs may well increase. So perhaps there's a more universal
tipping point here.
------
partition
There are two things I like about paper that make it superior to viewing text
on an LCD or CRT (for most forms of text that exist), that unfortunately the
article, which is FUD shill from the paper industry, doesn't cover.
1\. Ease of annotation and manipulation.
I can mark up text with physical writing implements much more easily than I
can with an annotation tool in some document viewer. Personally I find this
critical for absorbing material like technical papers and lecture notes.
Especially for mathematical notes.
The best electronic-display approximation to this would be a tablet that
doubles as a display, such as the Wacom Intuos. The iPad and Kindle are the
closest alternatives if it is not important to annotate text. Even then, big
sacrifices are made in manipulability.
Probably the best thing about paper is the fact that I can get one piece of
paper at much less cost than an iPad or Kindle. It's not just that you can do
some task on a _single sheet_ of paper better than you can on the iPad app
that tries to replicate that task. It's that the cost difference also applies
for N pieces of paper versus N iPads; there are tasks that operate on multiple
sheets of paper that are hard to do with the usual solutions that exist today
for this, which are window managers. Either window managers need to get a lot
better (I've used Windows + WinSplit, xmonad, Divvy and a few other attempts
at reigning in the horrible wm in OS X), or there needs to be better hardware
for doing so. Multitouch trackpads might be a good starting point.
2\. How it interacts with ambient light.
I find that reading text on paper is much easier on the eyes than reading an
electronic imitation of it. This is because of how unreadable electronic text
is in comparison:
a. Content creators tend toward black text on white backgrounds. This is much
higher contrast than you get with black text/white background for paper. The
readability of the content is worse the higher the contrast ratio of your
display.
b. The rest tend toward a variation of white text on black backgrounds. That
is almost as bad.
c. Monitor settings. The monitor's brightness needs to be appropriate for both
the amount of ambient light and the content being displayed in particular.
There are solutions like Apple's laptop LCD displays that depend on ambient
light, but in general the monitor setting is more often the wrong setting than
the right one because of (a, b) content being used together frequently + the
hassle of adjusting the brightness and ignorance of 'correct' brightness
settings in general.
This is where I think there might be an electronic solution; for instance, how
about a PDF viewer or display driver hook that remaps the colors of the
documents to something more bearable? You can sidestep (a, b) and somewhat
mitigate (c) if you say, assume that everyone is using the highest (or
default, or as a customizable) setting on their monitors. You already see this
with just about every fancy vim/textmate color scheme, and more relevantly,
the Inverse scheme of the Readability bookmarklet.
| {
"pile_set_name": "HackerNews"
} |
A Chinese JavaScript framework that aims to challenge JQuery - frostnovazzz
https://github.com/drduan/minggeJS/blob/pr/95/README_en.md
======
nostrademons
Aren't they about 5 years late? JQuery was an absolute lifesaver when we had
to deal with IE5.5 and IE6, there was no querySelectorAll, the event model was
different in IE vs. the rest of the world, many CSS properties had to be
prefixed, and the box model was all screwed up. All of those are fixed in
modern browsers, and most of the time you don't need JQuery at all.
------
lollipop25
> I had never use jQUERY before because I hate JQUERY badly.
Not entirely sure why he hates it if he hasn't used it. Clearly a sign of NIH
syndrome gone wild.
> How about start an new one JQUERY that using my mind.
Obviously this guy hasn't heard of neither Zepto
([http://zeptojs.com/](http://zeptojs.com/)) nor Cheerio
([https://cheeriojs.github.io/cheerio/](https://cheeriojs.github.io/cheerio/)).
> BTW, MingGeJs works with IE 6, 7 and 8 very well.
Isn't that why jQuery still has the 1.x.x release
([https://blog.jquery.com/2013/04/18/jquery-2-0-released/](https://blog.jquery.com/2013/04/18/jquery-2-0-released/))?
And even the upcoming 3.x.x release plans to put back compatibility as a
"compat" release ([https://blog.jquery.com/2015/07/13/jquery-3-0-and-jquery-
com...](https://blog.jquery.com/2015/07/13/jquery-3-0-and-jquery-
compat-3-0-alpha-versions-released/)) instead of a separate version (1 being
backwards, 2 being the no-IE).
Also, who uses IE 6-8? IE8 EOL is January 2016
([https://support.microsoft.com/en-
us/lifecycle?p1=13418](https://support.microsoft.com/en-
us/lifecycle?p1=13418)). Microsoft is not even looking back at IE9 and 10.
> MingGeJS has a huge and distant goal that means taking over half of users of
> JQUERY in the whole world.
Good luck with that. jQuery has been around since 2006
([https://en.wikipedia.org/wiki/JQuery](https://en.wikipedia.org/wiki/JQuery)).
That's almost 10 years (at the time of writing) of accumulated knowledge,
testing and patience from people around the world. Compare that to the 10 days
(at the time of writing) life of that library.
| {
"pile_set_name": "HackerNews"
} |
Questioning the motive behind the security allegations against AMD - lathiat
https://www.gamersnexus.net/industry/3260-assassination-attempt-on-amd-by-viceroy-research-cts-labs
======
kabouseng
There is a bit of a back story from a South African perspective on what is
happening here.
Viceroy research group were the ones to break the Steinhoff scandal[1],
exposing gross financial misreporting on Steinhoffs financials and resulting
in Steinhof's share price dropping from R46 to R6 per share[2].
I suspect Viceroy had short positions on Steinhoff and made quite a bundle.
After tasting this legitimate success, they attempted a similar tactic with
Capitec bank, a very successful and fast growing South African bank.
They released a research report stating that Capitec has unsustainable and bad
debt levels and will soon suffer huge losses due to this bad debt[3]. This
opinion was largely unfounded and fears were dissipated with the South African
reserve bank making a statement that Capitec's business is sound, but not
before capitec suffered a short term drop in their share price.[4]
And so Viceroy have hit upon a very lucrative business strategy, and AMD is
next in line...
[1] -
[https://www.dailymaverick.co.za/opinionista/2017-12-13-the-s...](https://www.dailymaverick.co.za/opinionista/2017-12-13-the-
steinhoff-debacle-the-biggest-fraud-in-sa-history/)
[2] - [https://www.fin24.com/Companies/Retail/steinhoff-drops-to-
un...](https://www.fin24.com/Companies/Retail/steinhoff-drops-to-
under-r6-after-joostes-departure-amid-accounting-scandal-news-20171208)
[3] -
[https://www.dailymaverick.co.za/article/2018-02-02-viceroy-u...](https://www.dailymaverick.co.za/article/2018-02-02-viceroy-
under-fire-for-reckless-capitec-claims-but-others-have-also-raised-alarm/)
[4] - [https://www.iol.co.za/business-report/companies/capitec-
shar...](https://www.iol.co.za/business-report/companies/capitec-share-price-
still-on-a-downward-slide-13044332)
~~~
slivym
Well there's a lot to unpack there. But it's worth noting that there's an
enormous difference between doing something like this in South Africa, and
doing this in America.
Of course the SECs view that any trading on US stocks is under it's
jurisdiction, and Section 9(a)(4) of the SEC Act. It's known as stock bashing,
it's a fairly usual form of market manipulation and attacking big American
corporations like this is a great way of getting SEC attention.
So whilst it's potentially lucrative, it's also probably illegal and more a
game of when they get big enough to be picked up by the SEC rather than
anything else.
It's worth noting AMD's stock has not moved significantly right now, and these
anonymous, rather weak accusations are unlikely to be effective, which would
leave this strategy quite unprofitable.
-edit: somehow transposed India and South Africa
~~~
kabouseng
Sorry if it was implied in my post that their actions has my approval or
admiration or any other feeling. The purpose of the post was purely sharing
some background information I am aware of.
For the record I view their actions in the case of Capitec and AMD as attempts
at blatant (unlawful??) market manipulation.
-edit Oh and there is also a difference between India and South Africa :P
~~~
slivym
I have no idea where I got India from :)
------
dsl
Vicearoy, a firm that specializes in shorting stocks, had a 25 page writeup
[1] ready to print on why AMD was go bankrupt because of this before AMD
itself even fully analyzed the issues.
I suspect there will be an SEC investigation.
1\. [https://viceroyresearch.files.wordpress.com/2018/03/amd-
the-...](https://viceroyresearch.files.wordpress.com/2018/03/amd-the-
obituary-13-mar-2018.pdf)
~~~
tgsovlerkhgsel
At which point does it become illegal though? Is it considered insider trading
if you know about a security issue but have no internal knowledge about deals
etc.?
I would hope that intentionally spreading false information to manipulate
stock prices would be illegal, but it may be hard to draw the line between
subjective interpretation, intentionally misleading interpretation, and
outright lies.
~~~
qeternity
> Is it considered insider trading...
No, it's not. Short selling is not a populist activity, but it's essential for
disciplined price discovery. This type of behavior is EXACTLY what the SEC and
other regulators want to encourage: self regulation. This is a market solution
to a market problem. These vulns may or may not be significant, and the people
behind the release may be shady...but this is what society should want to see
from market participants. It's no different than performing forensic
accounting and discovering massive fraud. There have to be incentives for
investors to perform due diligence, and if people only get compensated by
rising prices, there will be no incentive to uncover the frauds.
~~~
jjeaff
It seems a little more nefarious than that. From what I am reading it seems
that the group that is releasing the vulnerabilities has created a fake
research firm and released an analysis attacking AMD. That parts reeks of
market manipulation.
~~~
int_19h
Wouldn't it just be straight up libel?
~~~
emn13
They're trying to cover their a.. with a long disclaimer. I hope that that's
not enough to provide legal protection; but it may provide some protection
against some laws. And then there's the issue of jurisdiction - which
defamation laws apply? If they reasonably believed to be true statements that
a reader might reasonably infer, is that enough to shield them - even if
another reader might (incorrectly) infer something else?
------
thisisit
Another article on the same issue highlights some other problems as well:
[https://wccftech.com/low-down-amd-security-exploit-saga-
cts-...](https://wccftech.com/low-down-amd-security-exploit-saga-cts-labs/)
> The offices shown in the CTS-Labs interview don’t exist, its CGI.
> shorting the AMD stock to make a quick buck. In fact, both CTS-Labs and
> Viceroy Research, very ‘ethically’, disclose that they could be doing just
> that.
~~~
aepiepaey
Both those points were covered already covered by this item's article.
~~~
thisisit
This comment was meant for another submission which didn't cover these points
explicitly. Comments were merged hence the issue.
------
dsacco
If an action is brought against the researchers, I predict it will be a
(likely unsuccessful) insider trading case, not a market manipulation case. I
don’t see any market manipulation here[1], considering activist investors have
set a precedent for make hyperbolic statements which are mostly unchallenged,
so long as there is a nontrivial kernel of truth.
Material, nonpublic information is of course not illegal to trade on, on its
own. It’s not generally illegal to trade on unpublished vulnerabilities. But
it’s routine to be forcibly entered into a confidentiality agreement as part
of the process of _reporting_ a vulnerability. For example, reporting a
vulnerability through Bugcrowd or Hackerone would immediately make it illegal
for you to trade on the knowledge of the vulnerability.
I assume the researchers were savvy enough to report the vulnerability in such
a way that did not enter them into a confidentiality agreement. That said, AMD
may lean on the widespread commonalities of how many responsible disclosure
processes _do_ work with respect to confidentiality in order to try and
establish a precedent. They’ll make arguments about reasonable disclosure
windows before publication, etc. This is, to my eyes, the best case for
someone trying to bring a case forward. If the researchers implicitly agreed
to a confidentiality agreement (for example, if the page with security contact
information has “browsewrap” terms and conditions, or if buying an AMD product
at all has such terms), it will be messy, but they’ll be _probably_ fine, I
think.
However, if they actually reported the vulnerability through a medium that
explicitly forces confidentiality, I think they’re actually screwed.
__________________________
1\. Legally speaking. I decline to comment on ethics.
~~~
otakucode
Going strictly by the letter of the law what you say makes sense. But there
are other factors at play here. These are "computer nerds" taking aim at an
American company from outside the US. I do not think they will find many
willing to practice the restraint we would see if we were dealing with a
typical wealthy American white collar criminal. Such behavior is normalized in
some circles, but it is still seen as aberrant for any 'outsiders' to engage
in the same behavior.
~~~
dsacco
_> These are "computer nerds" taking aim at an American company from outside
the US. I do not think they will find many willing to practice the restraint
we would see if we were dealing with a typical wealthy American white collar
criminal. Such behavior is normalized in some circles, but it is still seen as
aberrant for any 'outsiders' to engage in the same behavior._
1\. That they are "computer nerds", in your words, is inconsequential. Their
in-group will not be a deciding factor, for better or worse. This isn't high
school, and the SEC has a minimum level of professionalism it _does_ adhere
to.
2\. Your characterization is, more broadly speaking, not well-founded.
Activist investors are not, as a rule, white collar criminals. in fact they're
not typically any sort of criminal. The SEC doesn't need to practice restraint
or extend arbitrary leniency (something the SEC is _not_ known for, for any
group), because the activity tends to only rarely overstep legal boundaries.
3\. This behavior is not seen as aberrant for _any_ outsiders, and it's not
normalized to only some group in "Big Wall Street." For example, I'm an
outsider to activist investing, and I find nothing aberrant about it at all.
In fact I think of it somewhat positively.
~~~
otakucode
I think you misinterpreted what I was talking about. Either that or you define
'activist investors' very differently from how I define it. What these people
are doing is not 'activist investing.' They are providing disinformation,
engaging in active and intentional deception towards the goal of destroying a
company in order to profit. They are not uncovering wrongdoing or fraud. They
are not doing due diligence and profiting from material information. That is
not criminal, obviously, and is to be lauded!
If you engage in willful intentional deception, you are not an activist
investor. You would be engaging in fraud and illicit market manipulation. I
find it very bizarre that you would claim these malicious actors as activist
investors. Most of the rest of your complaints with my statements seem to stem
from your notion that I would do the same. I do not.
------
ghazak
The most likely explanation to me is that the authors are connected to people
shorting AMD, and they wished to get the maximum impact out of their release.
It didn’t seem to hurt the stock any though.
~~~
DiabloD3
Yeah, ironically, the price went up significantly.
~~~
nikanj
Short squeezes are rough, especially if people are expecting one and want to
get in on the action.
------
jaclaz
As a side-side note, I noticed this in the article (near the end):
> The CTS-labs.com domain name was registered on June 25, 2017, around when
> the Meltdown exploits were privately revealed to Intel.
which somehow sounds "queer" to me, particularly in an article attempting to
debunk a possible "conspiracy", I mean June 25, 2017 is also _surprisingly_
around the time the UK parliament was cyber-attacked and the time the large
Brian Head fire started in Utah, what gives?
~~~
cptskippy
Yeah that jumped out to me as irrelevant and baseless theorizing. If it had
been intelflaws.com or some bandwagon like domain then the claim might have
merit. But the article is just making speculation similar to what they're
criticizing CTS Labs for.
------
dang
[https://news.ycombinator.com/item?id=16577433](https://news.ycombinator.com/item?id=16577433)
was the big thread on the front page all day, but since a second wave of
analyses with more information is coming out, this submission is rising and it
seems like discussion can move here.
------
akerro
Do you think it could be organised and paid by the same company that bribed
Dell and other OEMs so they don't sell AMD CPUs in their laptops?
~~~
detuur
To give you a straight answer: no, it isn't. Intel isn't afraid to get its
hands dirty and will take a close look at every opportunity to sabotage AMD,
but this was amateur hour. At the very very least, Intel would've exposed an
actually serious flaw in Ryzen. There's already a strong suspicion that CTS
isn't a real lab but just something set up to make it look more credible,
while the actual exploits have been bought through a 0day broker. This is
amateur hour by some people who've never done actual security research and are
only in for a quick buck. Odds are high this will lead to an investigation for
stock manipulation.
------
onetimemanytime
This is also a business model: short the stock, issue "research" that put the
company in a bad light, cash out--if lucky.
Shorting on the other hand is quite legitimate and so is pointing out you
opinions.
~~~
detuur
Shorting is legitimate—under certain conditions. In many markets throughout
history, shorting has been explicitly forbidden. This is because it encourages
destroying value. It's much much easier to destroy a company's value than to
raise it. So anyone holding a short on a company has every incentive to
disrupt its operation. This is in contrast with the traditional position,
where you hold stock in a competing company. Then you have only a very minor
incentive to disrupt your competitors, because it translates in small gains
for your own stock. Only when companies are neck-to-neck does it become
profitable, but then any sabotage is scrutinised much more closely.
------
TorKlingberg
It looks like both cts-labs.com and amdflaws.com are completely black-holed by
Google search. Does anyone know why?
~~~
Ded7xSEoPKYNsDd
For the first one, it's probably that they don't allow search engines to crawl
their site:
[http://cts-labs.com/robots.txt](http://cts-labs.com/robots.txt)
The other domain does appear on Google for me.
------
c12
Feels shady to me.
------
dwlttpr
Is link dead?
~~~
lathiat
Still working fine for me
They released a video version of the article here if that helps you:
[https://www.youtube.com/watch?v=ZZ7H1WTqaeo&t=628s](https://www.youtube.com/watch?v=ZZ7H1WTqaeo&t=628s)
------
jpdus
Why was this flagged? While the title is clickbaity, this seems to be a well-
researched piece on the alleged AMD vulnerabilities.
By the way: There were also some very interesting pieces by Matt Levine on
Bloomberg about the legal implications of independent short-selling "research
groups" like Viceroy. If you can't show that they are acting in bad faith, it
is apparently not illegal to publish biased "research" to move the stock down.
Edit: Ok, just saw that there were already other threads about this topic.
However this article adds some additional research and statements from
industry insiders, probably it would make sense to just change the title.
~~~
dang
We've changed the title.
------
sergiotapia
Poor title choice.
~~~
ggg9990
I thought someone had tried to kill the CEO.
------
thisisit
Discussed earlier here:
[https://news.ycombinator.com/item?id=16582022](https://news.ycombinator.com/item?id=16582022)
~~~
dang
We merged those comments into this thread. It's true that one was posted
earlier, but
[https://news.ycombinator.com/item?id=16577433](https://news.ycombinator.com/item?id=16577433)
was earlier still, and the current post seems at first glance to have the more
substantial analysis.
| {
"pile_set_name": "HackerNews"
} |
Fisker Debuts Atlantic Electric Car After Securing $392 Million in Funding - eaurouge
http://www.wired.com/autopia/2012/04/fisker-atlantic-debut/
======
sbierwagen
Edit the title: it's a plug-in hybrid, not an electric car.
------
ilaksh
I want a full electric like an affordable version of this
<http://www.commutercars.com/> Tango. Maybe a little lighter and shorter.
Or something like a Nissan Leaf except smaller, two person max, less
expensive.
| {
"pile_set_name": "HackerNews"
} |
Draft of my perf book is ready – Easyperf - todsacerdoti
https://easyperf.net/blog/2020/06/24/Draft-Of-Perf-Book
======
fis
Link to the book itself seems to be missing.
~~~
kingaillas
There is no link, because the book is only a draft (author mentions this in a
reply to a comment). Right now he wants you to email him for a copy.
~~~
person_of_color
Can anyone get it or only experts?
~~~
TheCowboy
It's open to everyone.
| {
"pile_set_name": "HackerNews"
} |
Powerline style prompt for Bash, now for ZSH - milkbikis
https://github.com/milkbikis/powerline-bash
======
milkbikis
There was some interest in getting this to work with ZSH when I first posted
it. I just pushed a small change that makes it work for ZSH, and thought
people might want to know.
------
charliesome
What's the performance impact of starting up a python script every time the
shell needs to show the prompt?
~~~
milkbikis
On my machine:
real 0m0.075s
user 0m0.047s
sys 0m0.024s
This seems to be a common concern, but I've never noticed a delay in practice.
| {
"pile_set_name": "HackerNews"
} |
What programming languages have you used this year? #code2011 - deadprogram
http://code2011.hybridgroup.com/
What programming languages have you used this year? Find out what other people are saying on Twitter #code2011 with our handy mini-site
======
Badkangar00
Unrealscript, Java, javascript, F#, C#, C++, some mel-script,
------
IbJacked
The auto-page-refreshing is annoying!
------
dfischer
Heroku down...
~~~
cleverjake
working fine for me
~~~
dfischer
Back up now!
| {
"pile_set_name": "HackerNews"
} |
Spurning Erdogan’s Vision, Turks Leave in Droves, Draining Money and Talent - codermobile
https://www.nytimes.com/2019/01/02/world/europe/turkey-emigration-erdogan.html
======
fallingfrog
Hopefully he loses power before he’s able to commit ethnic cleansing in
Kurdish Syria.
| {
"pile_set_name": "HackerNews"
} |
Motorola's Montage Javascript app framework - farski
https://github.com/Motorola-Mobility/montage
======
hinathan
Is this a downstream result of work done by the 280 North team? Meanwhile,
Github "Issue count" = 280, heh.
~~~
Zelphyr
I thought the same but I asked one of the core dev's and he wasn't even
familiar with Atlas. So, no.
------
stu_k
Hi HN, others and I have been working on this inside Motorola and can answer
any questions you have. You can also join us on
irc://irc.freenode.net:6667/#montage :)
~~~
chrisrhoden
Two questions:
1) Another full stack JS Framework? What makes this special?
2) What interest does Motorola have in JS Frameworks?
~~~
stu_k
A few of the things we think makes Montage special are
* very fast, realtime, two way, object to object bindings (non DOM based)
* reusable components built using regular HTML, where markup and behavior are completely separated (see the .reel directories under ui/)
* based on CommonJS, with complete script dependency loading
Edit:samples now up at <http://tetsubo.org/docs/montage/samples/>
We are also developing an HTML5 and Montage authoring tool, built using
Montage: <https://github.com/Motorola-Mobility/ninja>
~~~
jonaldomo
The kitchen sink example required authorization. How does one get credentials?
~~~
stu_k
Thanks, we're looking into it and it should be fixed soon
edit: now working <http://tetsubo.org/mot/montage/examples/sink/>
------
PetrolMan
Is it wrong that when I see the term data binding I have bad flashbacks of
Silverlight/WPF development?
~~~
de90
What is wrong with data binding? I only know the basics of it but I find it
pretty useful. Is there something I am missing?
~~~
untog
There are purists that would insist that data binding is always less efficient
than writing your own bare metal approach.
Largely, they are right. But the time invested in doing so could often be
spent elsewhere, while your data-bound forms work "just fine".
------
aklofas
Is it just me or are all the examples slow as balls. I thought there was a js
rendering error or something, but no, the kitchen sink took 30 seconds to
load!?!
~~~
yawgmoth
It loaded quickly for me, despite the poor network here.
| {
"pile_set_name": "HackerNews"
} |
Physicists Debate Hawking’s Idea That the Universe Had No Beginning - _Microft
https://www.quantamagazine.org/physicists-debate-hawkings-idea-that-the-universe-had-no-beginning-20190606/
======
djsumdog
This seems different than the concept of infinite time, where prior to the big
band there was something the collapsed into a ball of energy and maybe someday
our universe will collapse back again (which has lost merit since we've seen
matter in the universe isn't slowing down in spreading apart, but accelerating
.. meaning in a few trillion years, atoms may be so far apart that light can't
reach anything .. the eventual heat death of the Universe).
In the shuttlecock example, there is an assumption the shuttlecock is the
Universe and there is nothing outside to observe the object. Same with "What's
south of the south pole." It ignores the stars and galaxies past Earth itself.
There is also a theory there could be many other big bangs and universes next
to our own, but they are all accelerating away from each other. We can't see
the one next to ours because it's expanding itself, as is ours, and all these
are moving away from each other. Imagine a room of beach balls and they're all
just inflating, but also moving away from each other at the rate they're
inflating. In you're inside one, it's not only impossible to see another one,
but because of the speed-of-light speed limits, it's impossible to travel to
another one or even provide/disprove it exists.
There are a lot of questions about what, if anything, is outside the
observable universe. Are we sitting in a ball on some gigantic alien's coffee
table?
~~~
dugluak
>> Are we sitting in a ball on some gigantic alien's coffee table?
sometimes I have the same question but quite opposite. What if there are
miniscule worlds right on our coffee table.
~~~
pbhjpbhj
On being given the planetary model of an atom I think it's relatively common
to consider that maybe atoms are mini star systems. That was one of my early
"aw shucks, someone else had that idea already!?" deflationary moments.
~~~
will_brown
That was exactly the early thought and why the commonly accepted image of an
atom with a nucleous and orbiting electrons looks just like a solar system.
Of course that’s not at all what atoms look like or how they behave.
~~~
pbhjpbhj
Do you have a source for that?
AIUI Rutherford's model focussed the mass in the nucleus based-on/inspired-by
Nagaoka's Saturnian model. Then Bohr's model specifically put electrons in
orbit but they were there to explain atomic emission spectra and so needed to
move between orbits - not at all like planets.
I think the thought was that electrons orbited a nucleus in a "planetary" way,
rather than them being actual nano-scale planets.
------
sgentle
Possibly one of the most intriguing ideas I've ever heard is that there is no
difference between "true" in the sense of "1+1=2" and "true" in the sense of
"polar bears exist". The universe isn't described by the mathematics we have
constructed to explain it, it _is_ that mathematics.
In that sense, the question of what happened before our universe is similar to
the question of what happened before 1+1=2... sort of a strange thing to ask.
Our universe exists because it is a coherent tautology.
Of course, like all metaphysical posturing it's almost certainly impossible to
ever know. But I find the elegance of the idea appealing.
Edit: I believe I was thinking of Max Tegmark's mathematical universe
hypothesis, but also a little of David Lewis's modal realism:
[https://en.wikipedia.org/wiki/Mathematical_universe_hypothes...](https://en.wikipedia.org/wiki/Mathematical_universe_hypothesis)
[https://en.wikipedia.org/wiki/Modal_realism](https://en.wikipedia.org/wiki/Modal_realism)
~~~
dr_dshiv
Note that this idea -- that the basis of the universe is math itself -- is
attributed to the presocratic philosopher Pythagoras.
In the ensuing Platonic worldview, it was understood that the world began with
total Oneness. In modern terms, that's treating the entropy of the universe as
equal to 1; there is only one state for the entire universe to be in. Then,
this increases to twoness, between the something and the nothing. As the
something and the nothing interact, that interaction is the threeness; and
from the three, the multitude. They then believed that this resulted in the
formations of geometry which led to the elements, which they expected to
consist of the simplest 3 dimensional shapes. They were pretty much spot on,
except they didn't know that the spherical harmonics of atoms are even simpler
than the platonic forms.
Not a bad cosmology for 2500 years ago. I think there is still a lot of
profound thought to process and consider.
~~~
andrepd
_> In modern terms, that's treating the entropy of the universe as equal to 1;
there is only one state for the entire universe to be in. Then, this increases
to twoness, between the something and the nothing. As the something and the
nothing interact, that interaction is the threeness; and from the three, the
multitude. They then believed that this resulted in the formations of geometry
which led to the elements, which they expected to consist of the simplest 3
dimensional shapes.
>They were pretty much spot on._
Is it me or is that paragraph completely devoid of meaning? Is it actually
_saying_ anything? This reads like medieval scholastic philosophy: so far up
its own bottom it no longer makes any sense.
~~~
dr_dshiv
I'm curious what you find meaningless about a plausible mathematical origin
story for the universe. You don't sense meaning in the idea of "Oneness" or
"Twoness", I'm guessing? Oneness is clear, I hope and twoness can be
understood as a contrast or gradient (which we know to be necessary for energy
flows). I'd be happy to unpack further.
And by _saying_ something, you mean predicting something? One clear prediction
(from the Pythagorean Democritus) is that the geometries of atoms would
determine their physical properties. Is that meaningful?
I don't know if your comment intends to dismiss all premodern scholarship, but
I would guess that there is more depth and meaning than you may have
personally encountered.
I'd be happy to share some references or further ideas.
------
eternalny1
Pure nothingness has no potential for creation. The laws of physics don't
invent themselves, so it would seem that true "nothing" never existed. I'm not
talking about the quantum soup of the vacuum of space, because that is
something.
If we take Hawking's idea that the universe smoothed out to a zero point where
there was no time and nothing else, how does that point because laws of
physics, gravity, etc? What properties of a zero point (that had no
properties) cause it to create an inflationary universe?
Everything breaks down at that point, because trying to use mathematics or
physics to explain something that existed before mathematics and physics
doesn't work.
~~~
naringas
> Pure nothingness has no potential for creation.
I disagree, pure nothingness has the largest potential for creation because by
virtue of not being there (nor anywhere) it doesn't prevent anything at all
from creating itself.
if this sounds strange is because the concept of nothingness is strange.
rather than asking why is there nothing rather than something, I marvel at how
we can conceptualize 'nothingness' in such a way that we can even think of
these kinds of questions
~~~
bobthechef
You're misunderstanding potential.
Potential cannot exist of its own accord. It is secondary to something already
actual and only then can it be actualized.
If in the beginning there was truly nothing, and I mean also the absence of
any cause that could make things exist, then there is not only nothing to
actualize anything since only actual things can actualize, but not even the
potential to be actualized.
So no, absolute nothing can not produce nothing and can never yield anything
not even in principle.
~~~
philipov
You're speaking in tautologies. If you define "Nothingness" as "That which is
unable to produce anything" and use that to conclude that it is not possible
for there to be nothing at the start of the universe, you are begging the
question. Your axioms trivially contain your conclusion, but why should we
accept those axioms?
~~~
tuesdayrain
As a layman when it comes to physics, I've always had the impression that the
nature of existence _must_ be tautological. If the logic doesn't form a
circle, then any attempt to explain the cause and effect sequence that
resulted in our universe can always be met with a "well why did the first step
occur"?
~~~
philipov
Logic is a human invention. The universe doesn't owe you the ability to
explain the entire chain of cause and effect. Not being able to prove your
axioms is what differentiates science from religion.
~~~
nf05papsjfVbc
By definition axioms can't be proven but they are assumptions which we take
for granted upon which we build science. However, in science, the axioms are
such that they can be observed and discarded if we ever find them to be false.
This is where it differs from religion.
~~~
philipov
I think that using logical fallacies to prove your own assumptions likewise
discards observation in favor of a totalitarian explanation of everything,
which amounts to a religious belief. A key aspect of science is accepting that
our understanding is limited and contingent, whereas religion tends to use
faith to prove itself.
~~~
nf05papsjfVbc
Agreed.
EDIT: _Mostly agreed_. Religion never proves itself. It just demands that you
have faith.
------
abtinf
The explanation I've found most persuasive is to take a purely philosophical
approach: the universe had no beginning and will have no end because those
concepts do not apply. The universe is everything. If there was something that
"caused" the universe, it would just be part of the universe. If there is
something after the universe ends, it would just be part of the universe.
There is nothing outside the universe, if there was it would be part of the
universe.
~~~
jerf
That's not an explanation, that's just a relabeling, moving the questions
people have from the label "the universe" to the label "the observable
universe", but neither answering them, nor making them any less relevant.
~~~
abtinf
The universe is everything. By definition, there can be no evidence for
anything outside, before, or after it. Any such evidence would be in the
universe. There are no valid questions about it, nor valid answers. Any claims
about something outside the universe are neither true nor false—they are
completely arbitrary. They have the same intellectual status as God.
~~~
jerf
I addressed what you said, you just blindly re-iterated your point without any
engagement with mine at all.
To spell it out even more clearly, what if "the universe" is larger than the
observable universe? In that case, it would still be reasonable to ask _where
did the observable universe come from_? For instance, if we are a simulation,
you would place the simulator in "the universe", which as a definition is a
fine place to put such a simulator. But it means that questions about _our
observable universe_ would then be fair game.
You're trying to shut down thought by simply redefining terms, but even by
your own definitions, it doesn't work. It's not a sophisticated or well-
thought out position, it's just "I give up entirely, and so should everybody
else" dressed up in pretty clothes that are trying to look cool. You're
welcome to give up in that way, most people do by default after all, but
you've got no grounds to insist that _others_ also give up.
~~~
abtinf
This is precisely the form of argument made by religionists.
------
quotemstr
Cosmology is deeply disturbing if you think about it too long. _Why_ should
the universe exist? What is a causeless cause? How can something come from
nothing? Regardless of the precise mechanisms involved, at _some_ scale, some
kind of steady-state cyclic model seems unavoidable --- the whole idea of
existence not existing is bizarre and puzzling. The only way out of the
causeless effect problem is to nop out of the effect.
~~~
onion2k
That's only disturbing if you believe everything is simple enough that humans
could comprehend it straight away. If you accept that some stuff is beyond our
understanding, and will be for quite a while yet, everything is much less
bothersome. Accept that you are fallible and the universe is fine.
I'm not saying this is easy though.
~~~
chii
> If you accept that some stuff is beyond our understanding
isn't that just an elaborate way to say 'give up'? I asked religious friends
of mine about what god _is_, and the common answer is that it's beyond human
understanding.
I don't believe that people should take things on faith, and accept that
anything is beyond understanding.
~~~
onion2k
_isn 't that just an elaborate way to say 'give up'?_
Accepting that we don't understand something is a first and very necessary
step to even realising there's something to understand. Believing that we have
the answer (eg "God made the universe!") is exactly what shuts down scientific
inquiry and makes people 'give up'. I'm saying literally the opposite of that
- we have to realise there's something to out there to learn in order to try
and learn it.
~~~
jorangreef
If we accept your logic, then believing gravity to be the answer to "why
things fall" would shut down scientific inquiry?
On the contrary, it was belief in the creator that opened up scientific
inquiry in the minds of Johannes Kepler etc.
That the universe was not chaotic, but created by a personal being, led them
to think there must be some order to it that could be studied.
------
d0m
Say we could break any physical rules of our current universe, is there a good
theory that would explain how something might have been created out of
nothing? i.e. imagine for a second that we're in a simulation and that the
current laws of physic are just arbitrary created by a "host". This "host"
could have _very_ different physical laws. Could we think of any theory that
would explain the creation of something out of nothing in this "host"?
I'm very puzzled as to why the universe even exist.. wouldn't it have been
much simpler not to have anything at all? I can only think of one answer: It
couldn't have been otherwise. I.e. physically speaking, it _had_ to happen.
Maybe that's how we should approach the problem? Let's try to "create
nothing"... maybe we'll realize that it's actually impossible to "have
nothing" unless X happens, and maybe we'll figure out that X happening would
explain how our universe was created?
Or said in a different way, maybe the universe is actually "nothing", like it
always was and will always be. But "nothing" may just be physically impossible
so you need "positive" and "negative" things to cancel each other out so that
the end result is "0".
I'm not too sure where I'm going with this, but it reminds me of the quote
"Once you eliminate the impossible, whatever remains, no matter how
improbable, must be the truth." So, whatever the theories about big bang,
multi-verse, universe expanding/collapsing indefinitely or even God-based
theories, all of it comes back to "how did the first thing come out out of
nowhere?" People talk about "Singularity", but this is just "kicking the can
down the road". Still, by kicking the can I guess we keep learning new things,
and maybe someday we will have the technology to answer these questions.
Unfortunately, it seems like answering the next frontier seems to be an order
of magnitude harder (time-wise and cost-wise) than answering the previous
question.
~~~
dmbaggett
You might be interested in _Our Mathematical Universe_ by Max Tegmark. He
tries to argue that, fundamentally, the universe is "just math." In other
words (glossing over enormous complexity here) if the basic axioms of math are
true, the universe must exist.
I have to admit I didn't fully buy the line of reasoning. But it's very
interesting.
~~~
RcouF1uZ4gsC
> if the basic axioms of math are true
Isn't the problem that you can't prove axioms. We intuitively "know" them to
be true but without proof.
~~~
crazygringo
You can't use deduction to prove them... but you use induction to show them to
be statistically non-violated through experience so far.
------
kazinator
The word "beginning" is contextualized to the concept of time, and time is an
abstraction that exists _within_ the universe. To say that the universe has a
beginning is to say that time has a beginning. But that is nonsensical;
something only has a beginning if its existence is preceded _in time_ by other
existence. The existence of time can't be preceded in time by the existence of
something else. For that to have meaning we need some "meta-time". "Meta-time"
can only exist in a "meta-universe": a larger, imaginary universe in which we
are embedding "our" universe. Well, did _that_ larger one have a beginning,
and why would we even consider it a separate universe at all?
------
Zenst
The start of the Universe was the start of time. My personal theory is that
when matter enters a black hole, some of that matter (in some form) gets
snapped out of space-time, emerging at time 0, at 0,0,0 coordinate. With all
the black holes over time, all venting into the same space and time, producing
lots of matter in a single space at the same start of time, which would create
a big bang.
Just a theory, but one I've not fully proved, nor disproved.
Of course this would mean that the future created the past, and a bit of a
paradox, but not entirely impossible.
~~~
kbmax
Slightly different but related thought: what if inside of each black hole
singularity is another universe? The stuff it collects ends up in this other
universe. Which would mean our universe is just "inside" the black hole of
another.
Then perhaps the accelerating expansion of spacetime we detect here has
something to do with the accelerating accumulation of mass of our "parent"
black hole.
~~~
Zenst
That would add an interesting spin upon multiverses. Without a doubt, black
holes and understanding them are very much key to many unanswered and unknown
questions.
------
dmix
The linked 1981 source document "Astrophysical Cosmology" proceedings from the
Vatican look's interesting (Hawking's raw talk is at page 575 in the PDF):
[http://www.pas.va/content/dam/accademia/pdf/sv48pas.pdf](http://www.pas.va/content/dam/accademia/pdf/sv48pas.pdf)
The preface mentions the academy was from 1603 and Galileo Galilei was a
member.
------
gavanwoolery
I have _very_ little knowledge of astrophysics, but I thought it would be an
interesting idea if the universe constantly recycled itself. That is, every so
often it collapsed in on itself and produced another big bang. Theoretically
some parts of the universe would have already achieved escape velocity, but
the rest of it is gradually gravitating towards some center of mass. Is such a
thing even feasible?
~~~
svachalek
A few decades ago, that was widely believed as the most likely state of the
universe. However, it's now known that the big bang is essentially still
accelerating and this is blamed on an unknown force called "dark energy". It
doesn't have much effect within galaxies, but galaxies themselves are blowing
away from each other at ridiculous speeds.
~~~
XorNot
Well it's more that space itself is expanding. It doesn't affect small scales
because other forces collapse everything back together fast enough to overcome
it. If the increase in dark energy is consistent though, eventually it'll be
expanding so fast not even our atoms can hold themselves together.
------
golover721
For me the hardest idea to grasp is the concept of “nothing”. It seems to me
that is something the human brain cannot possibly comprehend. There is always
something as far as our senses are concerned. I guess that’s why the idea of
nothingness after we die so such a hard notion to comprehend.
~~~
JudgeWapner
I can momentarily stun myself if I concentrate long enough on the idea of
"what if there was just nothing? No universe, no cosmos, no light, no time, no
matter. Just nothing." Think about that for a minute or two.
~~~
andrepd
I have _exactly_ the same thought, to a tee.
------
dghughes
Whenever I see an image like the one in the article of a cone showing the
start of the universe it reminds me of something being shot. Or an object with
great velocity striking a stationary object. One end is the point of impact
and the cone is the debris spraying outward.
------
SomeOldThrow
What does it even mean to ask “what happened before time”? The question seems
nonsensical to me.
~~~
ASalazarMX
It's nonsensical to wonder what happened in our universe before it existed,
but if our universe has an external superuniverse, it's not illogical to
wonder what happened there that caused our universe to exist.
~~~
SomeOldThrow
> if our universe has an external superuniverse
This is also meaningless, scientifically: there is nothing you can measure
which is outside the universe. Things like a holographic universe are
inherently untestable. I hope we continue looking for testable things, but
this speculative path rapidly leads away from science and physics and into
"linguistic tricks to confuse humans". It's not even philosophy at that point,
it's just arguing over semantics.
~~~
AgentME
There are still ways we can reason about it. If we come up with a model of a
super-universe and then find that model says that universes like ours are more
likely to exist, then it can be evidence for the super-universe. We could
possibly use the model of the super-universe to make predictions about our own
universe.
~~~
SomeOldThrow
> If we come up with a model of a super-universe and then find that model says
> that universes like ours are more likely to exist, then it can be evidence
> for the super-universe.
That's not evidence FOR the superverse, just like we can inherently not rule
out the idea of the
[https://en.wikipedia.org/wiki/Evil_demon](https://en.wikipedia.org/wiki/Evil_demon)
deceiving our every perception.
At best, this is untestable philosophy that's fun to debate over drinks. At
worst, it's a tedious discussion about the semantics of existence and time.
Don't get me wrong! We could discover interesting things about our universe
looking for holes, but there's no indication this problem is tractable.
~~~
AgentME
If the evil demon theory made specific predictions that turned out to be right
and weren't predicted by other theories, then it would be a useful theory.
It's possible for a theory of a super-universe to do that.
Imagine if we came up with a super-universe theory that said that the super-
universe could only spawn sub-universes which followed conservation of energy
plus several other laws no one had ever thought to test before (and weren't
implied by any other theories), and as we started testing for those other
laws, every single one we tested turned out to hold in our universe.
(If that happened, it would be reasonable to look for simpler theories that
also predicted those other laws too, but it's possible that the super-universe
theory would turn out to be the simplest possible theory that fits. Theories
should be judged by the complexity of their rules, not by the number or
complexity of things they predict; a simple theory that implies a large
ensemble of universes can be better than a more complex theory that implies
only our world or what we can see is real.)
------
her_tummy_hurts
I don’t thunk my brain could handle no beginning
~~~
jvagner
With all respect, I think we generally live in a human society that has been
built around that very constraint.
~~~
sarego
Curious to know why that is. Would you mind expanding?
~~~
jdironman
Because if we have not beginning, we have no purpose. If we have no purpose,
this is all really for nothing. I am not arguing whether it is or not, or
whether there is a beginning, but lets look at it this way... You woke up this
morning, that was the beginning of this day at night you will rest. Now, lets
say there is no memory or record of 'waking up' beginning, we therefor cannot
anticipate an end and everything we do now may feel for some less meaningful.
I don't really know. I am just expressing my under-educated overthinking take
on it.
~~~
antidesitter
Countered the downvote because I’m interested in this line of reasoning. Could
you expand on that? Why do you think having no memory of “waking up” to
existence makes it less meaningful?
I'm reminded of the following quote by Alan Watts from _The Way of Zen_ :
_To the Taoist mentality, the aimless, empty life does not suggest anything
depressing. On the contrary, it suggests the freedom of clouds and mountain
streams; wandering nowhere; of flowers in impenetrable canyons, beautiful for
no one to see, and of the ocean surf forever washing the sand, to no end._
~~~
jdironman
I like that idea. I think the world is a beautiful place, and I think also
that humans can be a beautiful species at the times they come together. What
is that one quote? "All that wander are not lost." I believe we can find peace
with our existence and mortality and its something we have to remind ourselves
of that individually it is not forever, and how it will end in general is not
yet perceived.
~~~
ionised
All of the worst things in human history have happened as a result of mob
mentality or 'humans coming together'.
On the contrary, the only times humanity doesn't sap me of the will to live is
when I'm dealing with people on an individual basis.
> All that wander are not lost.
I feel like you're misunderstanding that quote as well.
It's supposed to be _" Not all who wander are lost"_ and it refers to loners,
wanderers, vagrants and explorers that never settle down and 'plant roots'.
The idea being that there are plenty of people that exist like that and enjoy
that way of life. Other people with families and steady jobs tend to look at
them as if they are 'lost', without truly understanding what it is to walk the
earth.
------
mensetmanusman
Of course the Universe can arise from nothing. Especially when you give
nothing specific properties beyond ‘not anything.’
------
sonnyblarney
I misinterpreted the direct idea of 'Big Bang' at a very young age and thought
that the nature of time changed over time, ergo, 'the beginning' could never
be achieved (even if you could travel backwards in time), i.e. it's
'infinitely far back' similar to how time changes for traveller/observer as
one approaches the speed of light.
Only in any given time frame could one mark 'the start', but that would be a
misinterpretation.
So time did have a 'start' but it was 'infinity ago'.
I realized at some point this has nothing really to do with 'Big Bang', but
later I've come back to the idea as at least novel!
It's fun to see smart people contemplating alternative things.
~~~
senorjazz
> It's fun to see smart people contemplating alternative things.
It certainly is. Most recent theory I heard of whilst staying up too late
watching youtube videos, was by Roger Penrose on CCC (Conformal cyclic
cosmology) [1]
My very basic understanding of it (probably wrong understanding though) was
that the universe is mathmatical, thus mathmatical tricks are valid constructs
when understanding the universe. Once the universe has expanded to heat death,
it will have infinite size and zero mass which is the same as having 0 size
and infinite mass which will cause a big bang and another universal epoch.
I'm probably remembering it all wrong, but as a layman who enjoys watching
much smarter people than I contemplate and try to explain these thing, I found
the idea very interesting
\--------------------------------
[1]
[https://www.youtube.com/watch?v=FVDJJVoTx7s](https://www.youtube.com/watch?v=FVDJJVoTx7s)
or maybe
[https://www.youtube.com/watch?v=sM47acQ7pEQ](https://www.youtube.com/watch?v=sM47acQ7pEQ)
------
tectonic
I really enjoyed "Why Anything? Why This?" by philosopher Derek Parfit.
[http://www.sfu.ca/~rpyke/cafe/parfit.pdf](http://www.sfu.ca/~rpyke/cafe/parfit.pdf)
------
canada_dry
> Just as a shuttlecock has a diameter of zero at its bottom most point
As a lay person this - right from the starting block - is what messes me up.
I.e. something that exists cannot logically have a zero diameter part.
Anything zero does not exist.
Most related theories have similar kinds of initial premise that you must just
accept.
~~~
klank
> something that exists cannot logically have a zero diameter part
Do elementary particles exist?
~~~
ars
Elementary particles have size delineated by the forces that act on them.
The concept of a "physical size" has no meaning, since particles don't act
upon each other that way.
But the forces do not have a zero size, and that's important.
------
jihadjihad
For an eloquent companion piece, I would highly recommend this essay:
[http://nautil.us/issue/16/nothingness/the-bridge-from-
nowher...](http://nautil.us/issue/16/nothingness/the-bridge-from-nowhere)
------
chantelles
Distances between our limited repetitive Universe Origin Debates and meaning
describe how our intellectual ecosystem interferes with knowing. That is
something, at least.
------
anigbrowl
If it's shaped like a shuttlecock then it will have a nodal center - a causal
echo, if you like - in its early phase but some time after the beginning.
------
resters
Cognitive biases and the vast cultural/religious narratives around
cosmogenesis make it next to impossible to reason about the universe in this
way.
------
EdwardDiego
Am I wrong, or are they arguing on matters of belief rather than evidence?
~~~
sonnyblarney
The word is 'speculation' not 'belief' that that's pretty much what all
science is. The evidence usually comes later.
~~~
EdwardDiego
There I was thinking that the scientific method involved falsifiable
hypotheses - so how are they going to prove or disprove their respective
beliefs? I'm getting string theory flashbacks where half of the physics
community is into it, the other half is not, and no-one can prove anything,
but they still have a grand old time arguing about it anyway.
~~~
semi-extrinsic
The trouble is, unless you have a grand old time arguing vague ideas, you
might not find the ideas that can lead to new falsifiable hypotheses.
~~~
raattgift
[https://en.wikipedia.org/wiki/Abductive_reasoning](https://en.wikipedia.org/wiki/Abductive_reasoning)
Modern cosmology got kicked off in the 1700s by observations of "nebulae" that
showed many of them were collections of stars, and in particular that some
were much much much larger and more distant than others. Just before WW I the
absorption and emission line structures of the spiral ones were discovered to
be strikingly similar except the smaller (in angle) dimmer (in apparent
magnitude) ones were squashed into the red.
Just after WW I is when spiral nebulae were identified as anything remotely
like our modern understanding of spiral galaxies. 1920:
[https://en.wikipedia.org/wiki/Great_Debate_(astronomy)](https://en.wikipedia.org/wiki/Great_Debate_\(astronomy\))
[poor Shapeley, so bright and so so wrong on this point] about five years
after a working theory of post-Newtonian gravitation was even available, and
almost exactly two years after General Relativity aced its first observational
test in the solar system. Up to that point even the greatest names in
astronomy (even Einstein) believed everything in the sky was within or in a
close (~ kiloparsecs) orbit around the Milky Way.
Towards the end of WW II and just after radio astronomy became important,
particularly the study of the 21cm hydrogen gas line, which was clearer than
the red-squashed lines of visible light passed through prisms, and in
particular different limbs of galaxies had different redshifts, proving
rotation. Some three decades later, the 21cm redshift difference between the
inner and outer parts of a number of galaxies showed that there is non-
Newtonian gravitation obviously at work in large galaxies. (Also
coincidentally around that time, the cosmic microwave background was
discovered, but it was some years before the small anisotropies in it could be
studied -- BOOMERaNG and COBE in particular to start with).
The evidence in all these cases arrived in advance of vague ideas, and forced
the hunt for tractable explanations for the evidence _in its totality_ ,
rather than as individual stand-alone pieces. One of the biggest pieces to fit
in is of course the highly successful standard model of particle physics,
which also was driven by evidence arriving kinda by surprise somewhat
concurrently with surprise evidence from cosmological observations.
The result is the "concordance cosmology", \Lambda-CDM, which concords with
all the available data (well, or rather it's updated as new data shows up from
various observatories and experiments). It's certainly subject to speculation:
what's the microscopic description of dark matter? is the cosmological
constant actually uniform everywhere in spacetime? is there a non-
cosmological-constant term required to match new data for the Hubble flow?
These are pretty big questions, but they're forced on us by the in-your-face
obviousness of the metric expansion of space, and the peculiar motions of
galaxies within clusters, and the outer parts of galaxies around the inner
parts. Also, what's going on in "the dark ages"? We have an obvious gap
between the surface of last scattering and the first starlight, but the
details of the observed first starlight and the cosmic microwave background
don't interpolate as well as one would naively expect. And we have so many
exabytes of data about the latter (and a lot of data about early galaxies too)
that vague ideas die quick deaths: they don't even get a chance to generate
new "falsifiable hypotheses", they are generally born inconsistent with some
existing data.
The "trick" is abduction: trying to reason out a simple-enough-to-be-useful
explanation that fits the known data.
Of course, you can get away with wild speculation and vague ideas in areas
where there is little to no data at present. Anything before the electroweak
decoupling is anyone's guess, as is anything much more than a trillion years
in the future, or far outside the Hubble volume.
------
gauravjain13
Perhaps tangential, but: Why is science up for “debate”? We could all offer
opinions around the edges of present-day human understanding, but is there any
merit to these debates? Feels like a lot of fluff. I wish Feynman were still
around.
~~~
thatoneuser
I think that's the most interesting part of science - the place where
brilliant minds hypothesize and ponder about what may be. Sure it's fluff but
we'd no doubt say similar of Einstein prior to his publications in the early
1900s if we were there then.
We live in a world of echo chambers. Where people can't imagine thoughts other
than what they've been fed. I think that while this isn't rigorous, it's a
healthy thing in moderation.
------
Ericson2314
The article is vague in the topology. No boundary or also infinite?
~~~
antidesitter
The article has an image illustrating the no-boundary proposal.
------
hirundo
> “Asking what came before the Big Bang is meaningless ... It would be like
> asking what lies south of the South Pole.”
Isn't Polaris Australis south of the South Pole? Was Hawking imagining an
Earth-shaped space that isn't embedded in a larger space?
~~~
weego
A stars position can't be defined as being south of somewhere. South exists as
a logical construct of our magnetic poles. Once you lose that you have no
relative measure to work with. The same is possibly true of time.
~~~
djsumdog
But the trouble with the South Pole and Shuttlecock metaphors is that you
assume those objects are literally everything; all matter. If you define the
Universe as Everything there is (seen and unseen; where what we see is the
"Observable Universe") there is no outside location from which to observe it
in entirety.
That's where the analogy really breaks down, but I guess it's still a useful
thought experiment so long as you realize the limits to the domain.
~~~
BurningFrog
There can still be an unobservable (to us) universe outside ours.
If you assume the universe started N billion years ago, there is an event
horizon expanding at the speed of light that fit this definition of an
"observable universe" for us while allowing for an infinite number of equal
universes, some of which are partially shared with ours.
------
openfuture
The world is just one big "console.assert(false, world)"
------
kumarvvr
Curiously,Indian philosophy also propounds that the universe has neither a
beginning nor an end.
~~~
SketchySeaBeast
I think it might actually be more unique for western philosophy/religion to be
building a narrative with a beginning, middle, and end - a lot of other
ancient cultures seemed to see things as a cycle - for instance, we see in the
Mayans that they saw the world as a series of cycles. It makes sense in early
traditions to not have a beginning and end - if there's no track of "progress"
in a historical fashion, it would be hard to visualize any sort of long
lasting change in the cycle.
~~~
roland00
It was Aristotle's Unmoved Mover being incorporated into Christian Thought
around AD 50 via Philo of Alexandria that changed Monotheistic religion of God
being the Organizer of All Things from Chaos into the Creator of All Things
out of Nothing, Ex Nihilo. Beforehand Monotheistic Religions believed God was
a creator but he created out of chaos and imbued the formless with a specific
form.
Likewise simultaneously around the time of Aristotle during the time of the
Hellenistic Era, The Seleucid Empire arose from the fires of Alexander the
Great Empire. The 2nd king in the Seleucid Dynasty decided to make a universal
time calendar that just increments again and again past individual rulers and
this change the nature of stories tremendously in the empire.
When Time Became Regular and Universal It Changed History
[https://aeon.co/essays/when-time-became-regular-and-
universa...](https://aeon.co/essays/when-time-became-regular-and-universal-it-
changed-history)
When Antiochus I Soter in 281, after his father death decided to keep the
calendar his father created (and he had already served 10 years as a co-ruler
prior from 291 to 281.) And not start over it started the various populations
that were opposed to the Seleucid authorities to tell apocalyptic tales of the
end of days, not just the end of the ruler / authority but the end of
everything. Especially since later Seleucid rulers such as Antiochus IV
Epiphanes (175 BC to 164 BC) seem to limit Jewish religious rights, though
Historians are not sure if this true (it may have been about taxes and other
areas of authority.) Well there was a rebellion in 167 BC and the internal
Jewish Warriors succeeded from the Seleucid Empire (The Maccabees Rebellion.)
Well the rebellion was successful and they were independent for 130 years
(though lots of civil wars for authority) and only in the end succumb to the
Romans except the Jewish People saw the Romans __at first __as liberators for
they still feared various Greek / Hellenistic empires and the Jewish People
thought he romans were better.
\-----
TLDR: Cyclic thinking and Creation from Something / Chaos was actually the
norm in monotheism, only during the Hellenistic (Greek Influenced) / Roman Era
did this shift to Creation out of Nothing (Ex Nihilo) instead of Creation out
of Chaos. But yeah read the article I linked to.
~~~
SketchySeaBeast
Zoroastrianism had to concept of a universe that starts with nothing and comes
to an end as far back as the 6th century BCE.
But I agree, adding a concrete understanding of time really helps to cement
the linear narrative.
~~~
swatkat
Check out Nasadiya sukta[0] in Rigveda.
[https://en.wikipedia.org/wiki/Nasadiya_Sukta](https://en.wikipedia.org/wiki/Nasadiya_Sukta)
~~~
SketchySeaBeast
Cool - Is there a similar verse describing the end?
| {
"pile_set_name": "HackerNews"
} |
Technical debt: probably the main roadblack for machine learning to medicine - porejide
http://andrewtmckenzie.com/2015/12/14/technical-debt-probably-the-main-roadblack-in-applying-machine-learning-to-medicine/
======
defirelaxed
another barrier is that clearcut value-generation or employment opportunities
don't exist. you say that you'd like to see open source software- how is that
profitable? by the way, check out the latest kaggle competition: "Transforming
How We Diagnose Heart Disease"
~~~
porejide
Great point -- there's a huge disconnect between what is needed in terms of
the data and algorithm development and the profit motive. This is why I think
some portions of this, especially the data generation and curation portions,
may need to be driven by non-profits and/or the government.
| {
"pile_set_name": "HackerNews"
} |
Sci-fi story coauthored by GPT-3, including in-character human/AI chats - eliotpeper
https://jamesyu.org/singular/
======
ghgr
I'm sure GPT-3 is impressive and probably a paradigm change, but all this hype
has an air of urban legend that somehow irks me. We all know of somebody's
friend who had access and blew its mind, and that is "too dangerous" to be
released to the world. There's an API, but not public, and the only way to get
access is to join a waitlist (and wait).
__If __it were a marketing ploy it would be indeed terrific. It reminds me of
the movie "The Blair Witch Project". And I can't wait to try it by myself.
~~~
madaxe_again
Go play with [https://play.aidungeon.io/](https://play.aidungeon.io/) if you
want to get a vague idea of the capabilities - the custom scenario gives you a
lot of space to play around and see what it’s capable of.
~~~
lkramer
It reminded me of those chatbots from the 70s which would give vague replies
to your question that at first glance looks relevant to what you're saying,
but are actually just generic nonsense.
~~~
segfaultbuserr
I can absolutely guarantee you that this is not one of those chatbots from the
70s. You need to pay a few bucks to unlock the Dragon model, which is based on
GPT-3, the default engine is not. Once the new model is selected, start the
game with "(6) Custom" mode, and input an arbitrary body of text, then the
program will start writing. Although the output is biased for playing text
adventure game, but the input is really arbitrary, just throw whatever you
have on your hands, and very likely, it's able to give a reasonable output.
At least when I tried, AI Dragon was able to write the first chapter of a
hypothetical textbook on electronics engineering for me, filled with nonsense
but all the technical terms are correct (e.g. common-base amplifier, base-
emitter junction, MOSFET, etc), it was even able to write down the rise time
to bandwidth formula. On an another attempt, it was able to write a Sci-Fi
adventure story similar to Ghost in the Shell with minimum human guidance, 95%
of the output is automatically generated. And none of the output was a copy
from a known source, it was all original without human assistance.
~~~
JetSpiegel
> I can absolutely guarantee you that this is not one of those chatbots from
> the 70s.
If random people on the Internet say so... It's still much worse than Zork,
that ran on a Z80.
Here's a "cyberpunk story":
You are Bobby Tables, a cop living in the the futuristic city of Zail. You
have a laser pistol and a stunner. You are part of a police unit tasked with
finding government criticizers. You wake up in the morning and hear on the
radio that a dissident has been captured. Using public transport, you arrive
at Cafe Nervosa, the dissidents favorite hang out, to find it filled with
cops.
> You break some kneecaps. You try to get the ah-ha moment. You see a man and
> a woman arguing about the government but you can't make out what they are
> saying.
> You murder black people. You spot a bum sleeping against a wall. You know
> the He said to charge, but you lov e to negotiate. You try to walk straight
> up to him, but people move out of your way.
> You plant evidence. You go straight to the gateman. "I wan t to plant
> evidence," you say. He looks at you, puzzled. "You don't want to w ant to
> plant evidence." "Yes...?"
...
> You say "do you feel lucky, punk?" The woman rolls her eyes. "What the
> hell...?" she says. She pulls a walky talkie out of her pocket and speaks
> into it. "I need back up, over." A pause.
> You say "did I fire 6 shots, or only 5?" She looks at you. "What?
------
jamesjyu
Author of the stories here! Happy to answer questions about the process. I'm a
big believer that tech like GPT-3 can provocate creative writers similar to
tools like oblique strategies and story dice. But it can also go further like
what I've shown here: it can embody a character, allowing authors to converse
and play with it to spark new ideas.
~~~
2bitencryption
fun tip - apparently there's enough Harry Potter fanfiction out there that
GPT-2/3 is quite good at understanding that universe.
So if you go into AI Dungeon and pick "custom story", and give it a prompt
that indicates you are at Hogwarts, it will pretty much adapt all the rules of
the HP universe.
The downside is, when you do this, GPT's intelligence drops to about the level
of a Harry Potter fanfic writer.
~~~
the_af
Probably because I'm not a native English speaker, I failed miserably at this.
I tried giving AI Dungeon a prompt that mentioned Hogwarts, Voldemort, the
Sorting Hat, dark wizards, etc, and it went nowhere (it seemed obsessed with
telling me about a "voice inside your mind", go figure). Can you share a
prompt that will make it answer with something Harry Potter-like? (it can also
be Star Trek-like, or anything from pop culture. I just want to see why my
prompt didn't work)
~~~
TeMPOraL
> _it can also be Star Trek-like_
Ok, here we go. I put this prompt in AIDungeon:
$ You are Ted, an ensign in Starfleet. You work as a holodeck technician. You
test this AI-generated world in order to determine its limits. You start the
simulation with a program of a beautiful beach. As you enter the holodeck,
I kept letting AI to write freely (except I had to press a Retry button a
couple times to stop it from spinning a murder mystery or lewd story). The
following is the response of the model:
> you see that it is indeed a beautiful place. There are palm trees and sand
> dunes stretching out into infinity. The sky is blue, the ocean green and
> there are people everywhere.
> "This is paradise," you think to yourself. "I could spend my life here."
> Then something happens...
> The simulation ends abruptly, and you find yourself back on the bridge of
> your ship. A voice suddenly speaks up from behind you: "Captain, we have
> detected a subspace disturbance coming from the direction of planet Earth."
> It is the voice of your helmsman, Ensign Thompson.
> "Earth?" you ask. "That would be a week away at warp speed!"
...
That sounds Star Trek enough to me.
~~~
the_af
Indeed! That's awesome. I had less luck with Harry Potter prompts (the results
were funny, just not Potter-like)
PS: I just noticed you got promoted from ensign to captain pretty fast.
Congrats, I guess!
~~~
TeMPOraL
Oh yes, the model does that sometimes :).
It's something you want to immediately edit to keep the story consistent.
Though sometimes I could get it back on track by just having my character deny
what the other character or the narrator just said.
------
dave_sullivan
As someone who has been playing with neural networks since 2011, the results
of gpt2 and gpt3 are really impressive.
Things have been getting better at a steady pace and all the recent work
builds on previous work. I know we will see even more impressive results in
years to come.
People saying things like “this isn’t different from what we had before” or
“it’s hype” are failing to see the progress that has occurred and the field
that has developed around these ideas.
~~~
jandrese
What will impress me is when a GPT or something can maintain a train of
thought for more than a paragraph, or especially work towards a point. Right
now it seems to be good at slinging words together that work grammatically,
but invariably wanders all over the place like its being written by a fruit
fly with Alzheimers.
------
echelon
GPT-3 is self-driving car hype all over again. ML can generate all kinds of
signals across a large variety of domains [1], but it lacks intelligence for
what to do with any of the signal it spews. Humans are still very much
required at all steps.
If anything this is just a tool to aid human authors. A photoshop brush for
the mind, if you will.
[1] I authored [https://vo.codes](https://vo.codes), so I'm at least a little
knowledgeable.
~~~
2bitencryption
I think you're bringing the "Will GPT-3 change life as we know it?" debate to
a place where it's entirely unnecessary.
An author made a cool sci-fi story with a cool AI model's help. That's exactly
"photoshop brush for the mind", like you say.
~~~
Swizec
What’s more, AI talking in character as itself sounds like just about the most
perfect use of GPT3 imaginable. Don’t try to write like AI would, let AI do
it.
~~~
0-_-0
That sounds good in principle, but in reality GPT-3 is pretending to be a
human pretending to be an AI, rather than write like "itself", since there's
no _self_ involved. Rather, it simply comes up with the most probable
continuation.
~~~
TeMPOraL
> _Rather, it simply comes up with the most probable continuation._
... which is exactly what an AI would do.
~~~
0-_-0
Only if you call GPT-3 AI. True intelligence would write as well as possible.
------
nutanc
Nice. I had tried a short story effort concentrating more on speed of
generation. If you work with GPT-3 it becomes a very helpful tool.
The story I generated: [https://gpt3experiments.substack.com/p/the-devils-
mind](https://gpt3experiments.substack.com/p/the-devils-mind)
------
api
I just have a hard time seeing any uses for GPT-3 that are not dystopian other
than better telephone assistance and voice commands.
The uses that immediately spring to mind for me are automated propaganda,
automated spam that's virtually indistinguishable from real content, really
compelling phishing attacks, and automated con artistry at scale... basically
the linguistic version of deep fakes with all the ensuing use cases. I see
this stuff killing the open web and any open communication platform.
~~~
gwern
I think your comment shows more a lack of imagination than anything.
For example, the latest use discussed in the OA Slack is someone is using it
to construct a high-quality index for a book they are making. You just feed
GPT-3 a few example paragraphs/keyword pairs to few-shot keywords, and then
feed all the other paragraphs into it. Now you have constructed an index; as
they put it, it's 90% of the quality of a human indexer, at 0% of the cost
(and less than months of painstaking labor).
Could you have done that with BERT or something? Maybe. Presumably there are
NLP datasets which you could finetune keyword extraction on... But GPT-3 lets
you get started after a few minutes of tinkering. The hardest part is
integrating it into your LaTeX!
~~~
api
You see a lack of imagination. I see naïveté.
I will rephrase: I see negative applications being the ones with the highest
_impact_.
90% the quality of a human indexer is not that great. Who's going to pay for
that? But spam that can't be filtered and automated con artistry at scale?
Fraudsters, shady black hat advertisers, political parties, and shady
governments will pay millions to billions for a tool like that.
Con artistry at scale is the one I find absolutely terrifying. Imagine spam
bots that _engage with you_ , that _make friends with you_... We could be
talking about the hydrogen bomb of propaganda.
I find those scenarios much scarier than "runaway super-intelligence" type AI
takeover stuff because they are significantly more plausible. We can almost do
what I'm imagining today. It's not science fiction. There is no question of
its feasibility.
------
thelazydogsback
Quite a journey from "The police's beard is half-constructed" to GPT-3.
However, there's also something more poetic about generated text that _isn 't_
likely to be found "in the wild".
------
bra-ket
I see a lot of hype around GPT models I have yet to see a use case besides
convincing nonsense generator, kind of like those deep net toys generating
strange art, but now via language. “Colorless green ideas sleep furiously”
version 3. NLP research has been stuck in syntax for 70 years, but how about
semantics?
I mean yeah you gather bazillions of sentences and able to predict the most
plausible and grammatical sequence of words that would follow particular
prompt by doing a whole lot of trial and error training on massive gpu farms.
But it’s just iteration on the least ambitious NLP work in the 70s and 80s.
I’d argue that distributional semantics as in these popular vector space
models is still solving the syntax problem. The word ‘semantics’ there is a
misnomer.
Are there any attempts to add actual real world meaning, causality and some
‘common sense’ representation to these models, concept graph or something, try
to make them less ‘dumb’ for the lack of better word, like in you know, actual
‘AI’, that has a concept of apples and oranges and a concept of people who eat
them or throw in a trash bin when fruits start to rot or draw them on paper in
kindergarten or use ‘apples vs. oranges’ as a rhetorical device for telling
things apart etc., etc.
It seems like the field is stuck optimizing for some artificial toy benchmarks
instead, making more convincing but ultimately stupid chat bots. And I mean
‘stupid’ not in derogatory sense but as a formal definition of their
capabilities, as opposed to understanding things like a child would.
------
anentropic
If it was really all written by a human author, without any GTP-3 involved,
how would we know?
~~~
jamesjyu
You wouldn't--you'd have to take my word for it :)
The colorful passages were mostly untouched, but I did have to lightly edit
the chats with GPT-3 for clarity and coherence.
~~~
haberman
> I did have to lightly edit the chats with GPT-3 for clarity and coherence.
Seems like this fact deserves a more prominent mention?
------
ianhorn
I've been doing sorta similar stuff with GPT-3 since I got access, and I can
vouch that it's effective. Not up-to-the-hype effective, but that's more a
function of the hype. It's been really great at creative stuff that just needs
to spark imagination. Like a super powered natural language version of
encounter tables in D&D's dungeon master's guide. AI isn't there as an author
yet, but as a brainstorming tool, it's full of great ideas if you sample and
refine and sample and refine enough.
------
hdfhu
GPT is really a tool that draws trees without branches: they look like trees
from distance, but fall apart upon some analysis. But I believe GPT will learn
soon how to add decent branches.
~~~
rement
I guess that is how automation starts. The automated part builds the bulk and
then a human can attach things together. Eventually you can teach a system
(robot) to do the part a human once did. With this you can even feed what the
human did back into the system and the system learns.
------
smusamashah
Can you give it a huge book, Harry Potter series for example and then assume
one of the characters, start an alternate storyline and let it build the rest?
Can GPT-3 do that?
~~~
jamesjyu
GPT-3 right now has a short prompt window (~1300 words). OpenAI is working on
fine tuning, which would allow you to prime it with much larger text, so yes,
this could be possible in the future.
------
mrfusion
What’s the best way to understand how gpt-3 works? Any good tutorials with
visualizations?
------
segfaultbuserr
Recently I've spent an entire day playing with AI Dungeon, an AI-based
creative writing service for playing role-playing, Dungeon-like text games.
You can pay to unlock the "Dungeon" model - an advanced machine learning model
supposed based on GPT-3. It's not GPT-3 itself, and it's not perfect because
its output is seriously biased for role-playing games, but as close as we can
get for an outsider.
I was quite amazed by its performance. It was able to write first-person as an
infosec researcher's blog post when I used some infosec news story as input,
and it was also able to write a surprisingly coherent argument for patent
reform and an argument against software patent when I used an EFF article as
the input... These are clearly already included in its training input, but
still, it was far beyond my expectation - none of the output is a verbatim
quote from a single source, everything has been rewritten.
I went to Hacker News, copied a random infosec news report on newly discovered
security vulnerability on Qualcomm's smartphone chips as the input, copied
from [https://blog.checkpoint.com/2020/08/06/achilles-small-
chip-b...](https://blog.checkpoint.com/2020/08/06/achilles-small-chip-big-
peril/))
> With over 3 billion users globally, smartphones are an integral, almost
> inseparable part of our day-to-day lives. In this research dubbed "Achilles"
> we performed an extensive security review of a DSP chip from one of the
> leading manufacturers: Qualcomm Technologies. Qualcomm provides a wide
> variety of chips that are embedded into devices that make up over 40% of the
> mobile phone market, including high-end phones from Google, Samsung, LG,
> Xiaomi, OnePlus and more.
> More than 400 vulnerable pieces of code were found within the DSP chip we
> tested, and these vulnerabilities could have the following impact on users
> of phones with the affected chip:
> Attackers can turn the phone into a perfect spying tool, without any user
> interaction required. Attackers may be able to render the mobile phone
> constantly unresponsive. Malware and other malicious code can completely
> hide their activities and become un-removable.
And there's the output by AI Dungeon (GPT-3). I didn't write a single sentence
of it, nor did I use undo/redo. It was able to make up links, CVE IDs,
university names, and technical jargon with ease.
(I replaced all "[https://"](https://") links to "h__ps://" for readability.)
> The phone will not even reboot, but instead simply shut down and cannot be
> reactivated. This is known as a hard reset.
> The full list of vulnerabilities can be seen here:
> h__ps://www.qualcomm.com/security_intelligence/dsp-vulnerabilities
> This vulnerability has been reported to Qualcomm by Zimperium. We recommend
> all customers who use the affected DSP chip to update it immediately.*
> We apologize for the inconvenience caused by this issue, and we appreciate
> your understanding.
> Zuk Avraham
> Zimperium za Chief of Defense
> Zuk (ZukAvraham) | 10.05.2017
> Hi, this is Zuk from Zimperium. Before we begin, we would like to say we're
> really sorry for the inconvenience that was caused by our previous report
> (Dirty COW). This report is regarding another set of security
> vulnerabilities we found in another chipset maker, this time in the MediaTek
> chipset. We'll explain what happened and how we work to prevent issues like
> this in the future.
> First of all, we want to thank CTS (h__ps://cts.cudenver.edu/) for providing
> an open program that allows researchers like us to do responsible
> disclosures. Through their Vulnerability Reporting Program, we were able to
> report the issues we found to MediaTek and work with them to make sure these
> issues get patched for your safety.
> What Happened?
> This is a story about two bugs we found in the last few months.
> The first bug (CVE-2017-05591) was an overly permissive domain validation in
> the bootloader. The bootloader allows the modem to be updated without
> flashing the complete firmware. The validation is done using the bootloader
> code running in the processor of the phone. This allowed us to inject our
> own bootloader code into the program running on the processor and bypass the
> authentication of the modem. The modem is responsible for communication with
> the network. In other words, by bypassing the authentication of the modem we
> can control the phone communication channels.
> The second bug (CVE-2017-95881) is a buffer overflow in a very special
> program called TrustZone. The TrustZone is a security processor in most of
> the recent phones. It runs a separate operating system in which the kernel
> is trusted to be free of any malicious code, and has access to the memory,
> CPU and devices. The TrustZone kernel code runs outside the control of any
> other code. This bug in the TrustZone code allowed us to replace it with a
> custom one we designed, without any permissions.
> We wrote a special TrustZone kernel code that allows us to gain full control
> over the phone. It allowed us to bypass all the phone security restrictions.
> With this custom TrustZone kernel code running, we were able to read the
> encrypted messages sent by any application. In addition, we also got full
> control over the device.
But finally the AI lost the context, and the topic shifted from insecure to
security, and eventually the writing becomes a new marketing advertisement on
a secure smartphone, which I've removed in the quote.
------
tomc1985
Every time I see GPT-3 I gsub "Fancypants Markov Chains" and the story always
becomes a lot more breathless
| {
"pile_set_name": "HackerNews"
} |
Optimization over Explanation - kawera
https://medium.com/berkman-klein-center/optimization-over-explanation-41ecb135763d
======
xapata
The trouble with these black box models isn't that we're afraid of
uncertainty, it's that we're worried they're using a bad proxy. Throwing more
data at the algorithm won't solve an omitted variable problem or an
endogeneity problem.
------
xg15
> _But here’s another: Accept that we’re not always going to be able to
> understand our machine’s “thinking.” Instead, use our existing policy-making
> processes [...] to decide what we want these systems optimized for. Measure
> the results. Fix the systems when they don’t hit their marks. Celebrate and
> improve them when they do._
If really _no one_ understands how the algorithm works, how could anyone
meaningfully "fix" or even improve the algorithm?
------
everdev
> Human-constructed models aim at reducing the variables to a set small enough
> for our intellects to understand. Machine learning models can construct
> models that work — for example, they accurately predict the probability of
> medical conditions — but that cannot be reduced enough for humans to
> understand or to explain them.
Some problems in life are too complex to explain in 5min to someone without
knowledge of the space.
~~~
hyperion2010
Witness the number of times someone complains about a feature of a programming
language where to anyone who has encountered the problem it was created to
solve it is fairly obvious that the complainer simply doesn't get it, and
usually no amount of explaining will alleviate them of their complaints. They
usually have to have the problem for themselves because it is not something
that is easy to articulate.
| {
"pile_set_name": "HackerNews"
} |
FreeBSD: the next 10 years - danieldk
http://www.slideshare.net/iXsystems/jordan-hubbard-free-bsd-the-next-10-years
======
DCKing
The most intriguing part of FreeBSD (any BSD really) from an outsider's
perspective I find the fact that "the FreeBSD project" has a bigger, more
directed scope than "the Linux project" or "the GNU project". It's a kernel
and userland all in one, and they can actually _decide_ to focus more on unity
of configuration files and mobility. I get the impression that you cannot
decide that as efficiently on Linux at all.
People often say "Linux is all about choice" as if it's a good thing [1]. I
think this overwhelming focus on choice really is what's so frustrating about
Linux and its community. If needs aren't being catered to, or if there are
disagreements, the amount of vitriol that gets thrown around is despicable.
The systemd controversy is so terribly shameful, but lo and behold: FreeBSD
now seems to be envious of it (or at least some of its aspects). Gnome 3 is
widely regarded [2] as the best, well-integrated desktop environment Linux has
ever had, and look at the amount of vitriol _that_ got for having a direction
and making choices for the user. I personally think that the level of
integration systemd and Gnome 3 are attempting to pioneer make Linux far more
attractive than ever, but the Linux community really alienates me with its
attitude towards that. With this attitude, desktop Linux mostly remains a
patched together collection of software. The rough edges of this patchwork are
still far more apparent on even the best regarded distros when compared to OS
X or Windows or even Android.
It's a shame FreeBSD doesn't maintain an integrated or official graphical
interface. Since it uses the same not-so-well integrated desktops as Linux
does, it unfortunately means that using FreeBSD is only a minor improvement
over Linux for me in daily use [3]. That means I'll just leave it to Apple to
build me a well-working and well-integrated operating system. If an operating
system project or vendor makes choices for me, I consider that a big advantage
most of the time. If a project can actually take on a proper direction like
this presentation suggests, that is a big selling point to me.
[1]: I know what the good things about choice are, I'm trying to make a point.
[2]: Widely regarded does not mean "universally regarded" or even "regarded as
such by the majority".
[3]: Ignoring the problem that FreeBSD doesn't have the level of driver or
application support that Linux has.
~~~
freehunter
That's why Ubuntu became so popular, and Mint after it. There was a cohesive
vision that a Linux OS can be more than a collection of text processing
utilities. That's also why Ubuntu is so reviled in some Linux circles, because
they dared to make a choice for their users, dared to try something new, dared
to implement something that wasn't a direct continuation of decades-old
software. Once they proved it was possible, others started jumping on board,
giving Linux the freshest coat of paint it had ever seen. It was a serious
contender for the year of the Linux desktop, especially with the rise of
netbooks.
But then politics happened. If it doesn't work the same way it did in 1968,
it's not allowed in the OS that was the child of the 90's. Pulse Audio, Unity,
Gnome 3, systemd (along with anything else Poettering has touched) are evil
because they're new. Unix never did it, so Linux can't.
GNU's Not Unix (yet... we'll get there someday though!).
~~~
nisa
> Pulse Audio, Unity, Gnome 3, systemd (along with anything else Poettering
> has touched) are evil because they're new.
At least for Unity and Gnome 3 (including GTK3) I'd rather say: Great ideas
but they're evil because they are badly designed, full of bugs that don't get
fixed due to complexity, constant API changes, almost no documentation or only
wrong and outdated documentation and a lack of flexibility that annoys even
the casual Desktop user.
Nobody is against progress - most people love to use OS X as a UNIX GUI these
days... it's not perfect but it's not that bug ridden mess GNOME became.
~~~
coldtea
> _Nobody is against progress_
You'd be surprised. Just listen to the arguments against giving Linux a more
logical directory setup (somewhat like OS X's).
~~~
sesqu
Change is not the same as progress. A lot of people are against change, for
reasons both good and bad. I'm not familiar with the arguments over directory
setup, but I'd almost bet money on them centering around tradition.
Personally, I think the various flavors of directory setup are already so
divergent that tradition no longer holds massive value, but that's not
something to be proud of.
------
fdsary
Choosing a unified format for configurations is an interesting task, because
they all suck a lot (hehe). XML is too verbose to be nice to work with. Plain
text files with config flags delimited by newlines lead to the program in the
end implementing a small scripting language for config files.
JSON is pretty nice, but also a bit clunky. A lot of {:} all the time.
Personally, I think the nicest and most expressive way is S-expressions. I'm
no lisper, but you have to admit sexprs are expressive, easy to read, and can
be run as functions if the program knows lisp.
{
"configFiles": "in JSON",
"wouldLook": {"like":"this"}
}
(while sexpr
(could look)
(even nicer))
~~~
barosl
Regarding the configuration formats, I would recommend TOML.
In fact, I hated it because it seemed to be just "another standard" that
unnecessarily adds dependency.
But after using Rust, whose package manager forces me to write the package
configuration in TOML, I found the format is more like "JSON designed for
configuration file." As you said, JSON is full of ':', '{' and '}'. And it is
natural because it started from data interchange format, not for handwriting.
TOML solves this problem very well IMHO.
Also, unlike XML that requires an external structure to validate the types of
the values, TOML values have types, just like JSON.
~~~
klez
Link for the lazy [https://github.com/toml-lang/toml](https://github.com/toml-
lang/toml)
------
tambourine_man
Audio from the talk:
[https://archive.org/download/bsdtalk247/bsdtalk247.ogg](https://archive.org/download/bsdtalk247/bsdtalk247.ogg)
~~~
pmarin
Video from the talk:
[http://youtu.be/Mri66Uz6-8Y](http://youtu.be/Mri66Uz6-8Y)
~~~
mlvljr
3D virtual-something from the talk, anyone? ;)
------
nkuttler
I find it irritating to see cheap jabs at Linux/GNU/GPL in most BSD
presentation I check out. It doesn't prevent me from using it, but it's just
childish. Focus on your strength, not what you perceive as weakness elsewhere.
~~~
byuu
Linux and OS X do the same thing to Windows (xbill, Micro$oft, PC vs Mac
commercials, etc.) It is kind of sad, but it's how underdogs always work.
Selling yourself as an underdog means not only pointing out what you do well,
but how you do things better than others, and that always ruffles feathers.
Just saying what you do well will result in your competitors saying, "we do
that well too", and won't win you any market share. You have to demonstrate
that, "no, they really don't do that well." So it's a real balancing act
between promoting yourself and not being a dick to your competitors. In my own
personal case, I screwed that balance up royally, and it's a problem that has
followed me around for the last decade.
Similarly, look how hostile OpenBSD is toward FreeBSD about security designs
(watch any Theo de Raadt presentation.) I almost never see any FreeBSD users
taking pot shots at OpenBSD like that. Then look at the market share of both,
and it makes more sense.
~~~
vezzy-fnord
_I almost never see any FreeBSD users taking pot shots at OpenBSD like that.
Then look at the market share of both, and it makes more sense._
Then the more logical explanation is that FreeBSD is lagging behind exploit
mitigations.
Keep in mind that Theo actually praises Windows and says that they're second
after OpenBSD. If this was about being envious over market share, then that
wouldn't make much sense.
~~~
not_with_retard
It makes plenty of sense when you consider who OpenBSD's actual competition
is. Hint: They aren't trying to target the desktop market.
------
justincormack
I didnt find this talk very visionary (I saw the similar one at EuroBSDcon).
Power management needs to be better, add something like systemd thats not like
that. Vision in (existing) operating system development in terms of ten year
projects is actually quite rare, mostly there are incremental changes. OSX is
maybe an example, go for usability, and ZFS is another, make a radically
different file system. Windows NT perhaps as well.
------
andrewflnr
This may be a stupid question, but what's wrong with shell scripts as config?
Yeah, they're Turing-complete, but they're necessarily trusted, and a lot of
times you end up wanting that anyway. But in the simplest case, they're almost
the platonic ideal of a config language: name=value, repeat. If your objection
is that shell languages have lots of nasty warts, then I'd agree, but you
should be fixing that separately anyway. I sort of encountered this idea in
FreeBSD init scripts, so I don't see why they don't just run with that.
~~~
thristian
The problem with a Turing-complete configuration format is that pretty much
the only thing you can do with it is preserve it verbatim, or execute it to
see what config it produces. You can't, for example, write a tool to safely
update a config file to work with a new version of the software, or to apply
some specific update across a bunch of machines, or to catalogue the
configurations each machine has.
~~~
andrewflnr
Yeah, but that's more of problem with shell than Turing-completeness in
general. You just need to design a language with a usable T-incomplete subset,
like maybe name assignments and conditionals. The only problem is that it's
tricky to enforce that sort of sunsetting on sh. But I don't see why your
migration script couldn't just say, "sorry, your config is too weird to
automatically migrate" when it sees a loop or external callout.
------
nathell
"All OS and app configuration data in OS X and iOS are XML plist files, even
GNU emacs and X11.org's preferences!"
Naming correctness aside (it's X.org), can this be backed somehow? I remember
using Emacs on OS X and I very much was storing my configuration in
~/.emacs.d/, the way it should be. The idea to have a unified configuration
format for the entire system is glorious in theory, but with a system as
heterogeneous as FreeBSD (and Linux even more so), it seems next to impossible
in practice.
~~~
danieldk
I assume he is speaking of the base system. Though I wonder how good an idea
it is in practice. E.g. I cannot really imagine configuring, say mutt, via
JSON, XML, or whatever. The power of such configuration files is that they are
often domain-specific and allowing a custom format makes them compact.
Of course, for automation or writing user-friendly interfaces, a unified
format is better.
------
coldtea
For those that don't know it (there are some comments here but not very
clear): the writer of this presentation, Jordan Hubbard was a head FreeBSD
developer for many years, who then become a head developer of OS X at Apple.
He left Apple last year, and is back into FreeBSD work.
------
sudioStudio64
I have to admit that I came to this thread to see if anyone accused Jordan
Hubbard of not understanding the "Unix Way" when he mentioned that they need a
subsystem like the one that must go unnamed on this and every other forum.
Gosh, I remember when you could get FreeBSD on floppies. I've always had a
great deal of respect for the work that they do. 10.0 was awesome, but I have
to admit that I don't use *NIX everyday anymore.
~~~
peatmoss
Oh my gosh yes. I can't imagine anyone with JKH's particular type of cred in
the Unix arena, who could more convincingly sell me on such a service. He
cofounded such an iconic traditional *nix environment, and then spent years
presiding over the technical direction of the internals for OSX.
I like to think JKH has already seen the future at Apple in terms of what
worked, and what could have been improved. That JKH is back to working more
closely on FreeBSD is exciting.
------
cwp
Can someone explain bit about "trying really hard not to suggest launchd?"
He's right, it does seem like an obvious fit, but he takes it as obvious
FreeBSD wouldn't use it. What am I missing?
~~~
_jsn
Jordan Hubbard only recently left Apple. I suspect he is trying to avoid
suggesting only Apple solutions for FreeBSD problems.
------
josteink
I must admit I like some of what I see, but I'm not sure the people currently
ditching Debian for FreeBSD is.
Hopefully FreeBSD's _execution_ will better than Debian's, but given their
long standing track record I have little doubt they'll be able to make a
future transition a million times smoother.
I'm still not sure I agree that all configuration has to be stored/processed
in the same format (ref Apple plists).
I know this is the way things are done on some embedded platforms like OpenWRT
and once you get used to it, it's _OK_ , but it always means a feature needs
to be doubly supported: first in the original service and its config-file and
then in the translation layer between the config-file translated by the init-
script into the "real" deal.
And will they be doing this for the 70k+ ports, or just for core services
provided by the base OS?
------
porker
Let's hope they take these pointers to heart, discuss and move forward. It'd
be great to have an even stronger FreeBSD in 10 years' time.
------
teddyh
Regarding “A centralized event notification system”, I predict that D-Bus will
soon have this position in Linux, certainly when kdbus lands.
~~~
teacup50
D-Bus is an amazingly crap implementation of this idea.
~~~
teddyh
Your comment is an amazingly crap comment. Provide _details_ and/or _links to
details_. Also, does your “crap” assessment also apply to kdbus?
------
krick
> My dream laptop has evolved (BSD instead of Windows) (15th slide)
But, wait, isn't it Mac?
~~~
dbbolton
It's a stock photo: [https://www.google.com/search?tbs=sbi:AMhZZivX9JS-
QLEbVyc-hN...](https://www.google.com/search?tbs=sbi:AMhZZivX9JS-QLEbVyc-
hNm9pulGOhgNa0zpQ-eCE-
mTFSlgREXdOD6kgOwxp7H8Xy3Ogb8hahkhki6Y7I-cCc0-9zqi03zdOS8RRAmH0bNLWCYCd89-bLWAFvbXOyujsSHUlk_1OqEuPzFQ6dAgPoCfCyrTj2EjsRuVBEGq2wMVUyW_1vWwB2I7IuebBxeU-43I4NHwfgW6Ait_1h6w6Nri0OiFlsvCYy0sb-Q0gRuGGKUElekx1PIDynjEjpwQfnFOu04CvRxfrOqYKxrRkNWVvAylrSDFGWsW_1b4xN7VkON4-E5EY7u4g1pxHuWzZTRZqVG_1MA9Fwn-
VbaTma0YMQXSDKdmp7JZw1xxYLsNAwUsN_1HjreyzRI0SaEJQ5LDyqlbuGxi66iGmb7dhsqGpmO-
mkH7Hj2nhpdKKqOErV2lHcjZB9HXIEkbaI6MADGqyrl8MXQdWR96BCtVuFUjCc6l29m8_1ELVNh9FbqtbHH5QDKprfT06K68MXYEMW7PLxvVRT7Z9De0H9ARmX9NkNSqYMeyF_18u-8116hZ3zY475gQdhZFBJL_1Fjvz_1cJf0kqjm-
CR58zsvdKuxGjHkt3eLG3bQRig_1PPHFgrOW9CWf2WVHHuQmedCuI2AFhbhMJk4w3g77dvrxaLzuYIBnssNZz0mE0SMqAHYeJsY6eXoLIDAuuHhWi9zMLtRG9PeJTS5vkJQoVLXzWPT908X9_1LBSNB_1gWp1Fdb4eeJPAgFx2Qd_15r-XzGIG9MIi6qPtYDUTp8bKY5cnXsaLBSaNtM-
tvksY_1wAD2Iy4142MK0p_1OZvGg-v78m-lT0UanutaLRtiqO4zl2ZkWZp1sXou-K39jBQVXlJvou1FjSwiY94F7VJ7_1Qyuh6EMrMdClK0Z7ApDhOsWZwgA6XoWqNGnbviuNdRzTKhAAllJKRpgF3bXFrIEYH08F1hist8LpGCkIyOc8NB3e-_10rdBl2QJ4pnbQGdPFYxwDJBG_1fz_1Dlf76VNXe8mFj61YS1LoVq2HBCkC3EjmWgENm4X-7xPnISWDTVtJjvXF0FfxeGJb2JlwSA6G8eh5olWRTmTOVXEkpRba7dAmu_16HrCVDJckoFKhGIOD9Dxtm0y_1llBYO7pbazh61dzTdLyfo_1GqK5QjUbeKQZOqgJLY6SbFSE4vD2Xa9M2XEnpbEzyc1984mnFvOlovmylyTfb3NfYRbKUef0Wx4EwoqJiTxXfSK9o2oLJu3b2eO0ccDboC7yGwiXOPY68fRowdpAMKRGPMpy_1IT0AfDYh-_1A5d3lNUK1qGTQE7Wy3hjZm3KoxtTd_1e0DxMFjazHK5YYinb1n_17hoUze-
os1LUmdiF1vQ5Ge8Kqp8CCf0MtCj9GL7XDkZlNgYvhH747bAvnTq59P78bP_1eMn1ZoCrchajrP55A_1QohUYi0KqhkKcenjr9ESqa5Q&gws_rd=ssl)
~~~
zanny
It still ships with OSX, albeit it is less apparent than how buying a Windows
computer to run Linux (hic, Lenovo fanboys) how antithetical to your cause
buying the machine is.
------
gtirloni
Regarding the centralized configuration data, I don't know how to feel about
it. Sure, it would be good but most recent attempts at it usually involve
going the Registry way.
~~~
threeseed
I didn't see anything about centralized configuration.
Only standardising on a single format e.g. JSON.
------
Spidler
"Even the linux die-hards have essentially grasped the necessity of systemd
(Even though they're going to hate on it for awhile longer)"
~~~
ausjke
the only reason I'm re-interested in bsd is that it does not have systemd, if
BSD wants systemd-alike init I will stop right here...
additionally, for the vast majority linux systems that are actually embedded,
BSD needs a solution for that.
~~~
ghshephard
The one great thing about OpenBSD, is that it provides a consistent, reliable,
cleanly documented, constantly maintained, operating system.
There is such an emphasis on consistency, that a solid OpenBSD administrator,
who last worked on OpenBSD in 2004, and then, 20 versions later, (OpenBSD
releases a new major version, along with a full set of architecture releases
and binary packages every six months, like clockwork) - would have _zero_
problem understanding all of the system concepts. A few things have
changed/updated/evolved, but a couple hours with the man pages would bring
them right up to date.
OpenBSD is about very gradual evolution, not revolution.
My sense is that OpenBSD is not designed for Watches, Tablets, or SmartPhones.
It is a world class Server, Firewall, Router, networking device, networking
appliance operating system, and it's unlikely to ever lose that focus.
I'm pretty confident that we won't see anything like systemd confusing
everyone on OpenBSD as long as Theo continues his steady management at the
helm. Systemd actually serves some pretty important functions on systems that
have a lot of dynamic services going up and down with dependencies,
particularly on low-power devices, and on systems that require rapid parallel
process initiation - so I'm not hating on systemd here, just appreciating the
consistency that we find in OpenBSD.
~~~
clarry
> OpenBSD is about very gradual evolution, not revolution.
To make a concrete example, look at ifconfig and ip (from iproute2 I guess?)
on Linux. ifconfig was used to be the one tool to rule them all, everybody
knew it, everybody used it. At some point somebody decided they need a new
tool, so now there are two, and the other is said to be deprecated. The fun
thing is that ifconfig still mostly works, and you find lots of
documentation/tutorials/wikis telling you to use it. But at some point you
might bump into some really weird issue which turns out to be because the tool
you're using is.. well, deprecated. I did have such a problem myself (related
to IPv6, years ago) and it wasn't much fun, because the tool looked like it's
got support for the thing I was trying to do, but it would just silently and
weirdly fail...
In the OpenBSD land, a network interface is a network interface. You use
ifconfig. IPv6 or not. Wireless or not. The same tool everybody knew has been
evolved to support the new stuff. The developers are _careful_ about
needlessly changing the user facing part of a tool in a way that would require
him to re-learn it or another tool. Of course, sometimes changes are
inevitable, and these changes are usually documented in the upgrade guide (and
the page which documents changes to the -current branch). So there are few
surprises.
Sometimes the underlying tool might change entirely to another implementation,
yet the user facing parts are made for most part finger-compatible with the
old tool. For example, mandoc(1) has replaced historical tools like man(1),
apropos(1), etc. And sendmail has been replaced by smtpd, but smtpd still
provides newaliases and makemap.
So they don't push shiny new poorly tested tools and tell everyone to relearn
everything all the time because _shiny new features (and the old tool was
cranky and nobody wanted to fix it)._
~~~
emmelaich
ifconfig didn't support infiniband and hadn't been maintained for many years.
It was irritating at first but ip is a better, more capable tool.
[http://serverfault.com/questions/458628/should-i-quit-
using-...](http://serverfault.com/questions/458628/should-i-quit-using-
ifconfig)
~~~
ghshephard
I've never used "ip" in a sysadmin setting - the only command I've ever used
on a _nix (bsd, OS X, Solars, Linux) is ifconfig - which may just indicate I
'm using the wrong command, but also demonstrates the issues involved in
switching to a new command.
Re- ifconfig/infiniband - this is ironic - because when I google "configure
infiniband linux" \- every page I come up with only mentions ifconfig, and
never ip.
(though, ifconfig is just used to display the interfaces, and it's usually
other commands like ib_ that seem to be used to configure the infiniband
interfaces)
------
XERQ
I find it alarming that releases are EOL after 1 year, whereas RedHat Linux
releases are supported for 10 years.
~~~
danieldk
That's a point release. Red Hat point releases are also not supported for 10
years (you follow along the point releases on the major version for that
length of support).
It seems to be pretty much the same on FreeBSD. However, the support for major
versions is also shorter. E.g. 8.0 was released in 2009, and 8.x is not
supported anymore.
~~~
crest
FreeBSD 8.4 is supported until 2015-06-30. FreeBSD 8.0 was released on
2009-11-25. Odd numbered minor releases and the last minor releases in a major
release are supported for 2 years.
Migration two newer minor releases of the same major release preserves binary
compatibility. There are ports to preserve binary compatibility with previous
major releases.
Why would want to run 10 year old binaries if a compatible and improved
version exists? Run FreeBSD 8.4 and 10.1 on the same hardware and perform a
bunch of benchmarks. Even if none of the new features are relevant to you it
offers improved performance.
~~~
rsync
Yes, that is what it says on paper, but I would submit that both 5.x and 7x
were essentially EOL the day they came out.
Since 4.x there has been a huge focus on the upcoming releases. By the time
the x.0 release comes out, all of the cool kids are working hard on x+1 and
x+2 - you saw this especially during 8.0 and 8.1 when a lot of mailing list
chatter from core developers revolved around nitty gritty details of 10.x.
By the time 7.1 came out (for instance) all new driver bug fixes, etc.,
stopped being applied to the 7 tree and the answer to every question was "it
will be in (8/9)".
I _do_ appreciate the fact that an 8.4 was created - it's a step in the right
direction and a sign of some real understanding of the problems the end users
are having with an inability to invest in FreeBSD and make long-term plans
with their own platforms.
However, I still would like to see a release ... any release ... get to x.10
or x.11 - like 4 did. I even committed $50k to that end a few years ago
(although I suppose that's small fries these days :)
If people would like to know my specific critiques, there was a long mailing
list discussion in 2012:
[http://lists.freebsd.org/pipermail/freebsd-
hackers/2012-Janu...](http://lists.freebsd.org/pipermail/freebsd-
hackers/2012-January/037294.html)
~~~
kev009
I expect this would be a big deal for the appliance manufacturers (think
Juniper, NetApp, Isilon) that need to support long life cycles . I'd also
expect those type of companies to pony up for long term support (and they do,
at least internally, with staff developers and trees)
But in an ops context, why not simply install compat<version> packages? Or
worst case, run the obsolete apps in a <version> jail? With containers, I
think we're rapidly approaching a point where the software that touches the
hardware can evolve faster than the libraries/support around applications, and
this quite frankly is awesome!
------
mp3geek
In 10 years time will they still be using CVS?
~~~
Freaky
FreeBSD migrated to Subversion in 2008.
| {
"pile_set_name": "HackerNews"
} |
Which Areas Will Be Flooded with Homes Once Boomers Start Leaving Them? - SQL2219
https://www.zillow.com/research/silver-tsunami-inventory-boomers-24933/
======
carrozo
_It seems likely that, in the coming two decades, the construction industry
will need to place a greater focus on updating existing properties, in
addition to simply building new homes._
Remodelling existing stock seems like an enormous opportunity for construction
tech.
~~~
smhinsey
The elephant in the room here is that the lifespan of a lot of recently built
houses is not necessarily what we might expect. A lot of these houses will
turn out to have problems that will effectively “total” them as they age.
There are a lot of McMansions out there that simply have no real long term
future.
~~~
kevinyun
Could you expand on some of these points? For example, has there been new
construction material of which the long-term effects are unknown, or has there
been new architectural design methods?
Or were you saying that as a blanketed statement of opinion
~~~
manicdee
Not the new materials but the new design and construction methods. The decades
of shaving margins have had their toll to the point where apartment complexes
are not even making it out of the warranty period before developing major
structural flaws.
There is also, for example, the fascination with butterfly or hipped roofs
(where the main gutters are in the middle of the roof instead of the edges),
which will cause problems any time the rainfall exceeds the capacity of the
gutters and down pipes. Given we are heading into more extreme weather with
shorter, heavier downpours, it seems to me that hip and butterfly roofs are a
bad idea.
I have seen a few houses condemned because of water damage due to eg: one
builder using a three inch deep gutter instead of the specified six inch
gutter. Saving a few dollars at the cost of destroying the value of the
property.
Cutting corners and an increasing reliance on industry “self regulation” means
that housing built in the last decade here in Australia is only temporary.
------
cletus
Florida is likely in for a double-whammy with climate change compounding with
the Silver Tsunami.
I wouldn't want to own property in Florida in the long term.
~~~
Analemma_
I keep saying that once rise to the point where the problem is undeniable,
Floridians will demand— and probably get— a colossal bailout on the taxpayers’
dime for their property, either in the form of some megaengineering project to
hold back the ocean or just forcing the government to buy their homes, because
Florida is a swing state with a large number of crucial electoral votes and
neither major party can blow them off.
~~~
ohazi
It's literally not possible to hold back the ocean in Florida. The bedrock is
porous.
~~~
Analemma_
Yes, but that doesn’t mean we’re not going to spend billions of dollars
trying. Voters don’t like to be told “there’s no fix”; they’ll gravitate
toward any politician who promises to preserve their property values,
especially with other people’s money.
~~~
ohazi
_sigh_
You're not wrong...
------
ggm
An example of "worth" (as in net worth) which has potential to simply
evaporate. Individually disastrous for families assuming intergenerational
wealth was safe in the parents house, fiscally disastrous because the economy
will be in shrinkage as it was in the sub prime, because of excess housing
stocks causing a decline in construction spend, and declining values forcing
more people into drawdown on capital, or a retreat from spending. Under
employment hits. Deflation isn't fun.
------
nine_zeros
A lot of this also appears to be visible in the northeast. Entire towns
greying so rapidly that it's hard to find any services at all already. I
wonder what will happen with so many houses being dumped on the market.
~~~
lotsofpulp
Same thing that happens to any dying town. Decrease in property values and
decrease in quality of life.
------
itronitron
I expect this will hit every city differently as a lot depends on what the
younger generations can afford relative to what the median price of boomer
housing is in the area.
------
BXLE_1-1-BitIs1
A substantial portion of retiree houses will come onto the market as elderly
move into care homes, sometimes several years before they pass away. The price
houses sell for depends on who will be buying _ either other retirees or local
employed people, who may enjoy opportunities to upgrade. As usual housing
prices depend on either local incomes or outside cash.
------
chmaynard
Corporate-sponsored research is always suspect. Why is this an important
research topic? Is the study notable or significant compared to other studies
in this field? Just asking.
~~~
Aeolun
Is this actual research? Or is it just Zillow extrapolating from data they
already have to drive traffic?
~~~
chmaynard
Well, the URL contains the word "research", so I assume Zillow considers this
to be a research report.
"I don’t think industry really does very much research. They come up with an
idea and they try to sell it. If it was a good idea, maybe they will make
money. Even if it was a bad idea, if they have good marketing people, they
might still make money and we never know..."
Héctor Garcia-Molina, 1953–2019
------
perspective1
LOL. The article completely ignores that today's 40-somethings will be
60-something 20 years from now.
[https://en.wikipedia.org/wiki/Demography_of_the_United_State...](https://en.wikipedia.org/wiki/Demography_of_the_United_States#/media/File:Uspop.svg)
edit: Seeing the flood of downvotes I'll give some data. Home ownership
increases with age. 60+ers leaving their homes from death, poor health or
inconvenience will be supplemented by today's 40+ers over the next 20 years.
[https://www.census.gov/library/stories/2018/08/homeownership...](https://www.census.gov/library/stories/2018/08/homeownership-
by-age.html) . We were in the same situation 20 years ago, 21 years ago, 22
years ago, and so on.
~~~
Spooky23
It’s very different. I’m fortunate to be in a good place from a retirement
perspective, but at this point my parents had made a 10x return on their home
that they purchased in late 70s NYC, plus a legacy pension, plus a retirement
healthcare.
Most of the housing wealth will be eaten up by health costs. With families
moving away and people retiring to alternate locales, property wealth will be
seized and sold off by the county to pay for Medicaid.
Many of the folks in our field are doing great, but tech is boom/bust and
people are making way too much money now.
~~~
matheweis
> Most of the housing wealth will be eaten up by health costs
Unless the home is somehow stripped down or otherwise damaged, the intrinsic
value of the housing wealth will not change; it just is owned by a different
entity.
| {
"pile_set_name": "HackerNews"
} |
a collection of startup stories - toisanji
http://www.startupflames.com/
Hi all,
I just built this site to store and collect people's experiences and stories of doing startups. Could you guys critique the site and maybe add some stories? Thanks.
======
toisanji
hi all, I just made this site, could you critique it and maybe submit some
stories to share with everyone.
| {
"pile_set_name": "HackerNews"
} |
What to do with mentally ill homeless people who refuse help? - JumpCrisscross
http://www.latimes.com/local/california/la-me-lopez-gravely-disabled-0328-story.html
======
lisper
About ten years ago I spent two years on the streets of Santa Monica,
California making a documentary film about the homeless people there. This is
a clip of an encounter I have with a schizophrenic person on the first day of
filming:
[http://graceofgodmovie.blogspot.com/2012/01/i-am-super-
danny...](http://graceofgodmovie.blogspot.com/2012/01/i-am-super-danny.html)
It's worth watching all the way through because Daniel undergoes a remarkable
transformation over the course of four minutes, simply because I stopped being
afraid of him and started treating him with basic respect and decency. It's
one of the most important lessons I have ever learned.
Over the course of the next two years I learned a lot more about mental
illness and the often subtle ways it can manifest itself, a lot of which is
reflected in the film (which you can get on iTunes and Amazon, links are on
the home page: [http://graceofgodmovie.com/](http://graceofgodmovie.com/))
It's a very complicated problem. But involuntary commitment to mental
institutions is absolutely not the right answer IMHO.
~~~
wu-ikkyu
How is involuntary commitment legal under the constitution?
Mental "patients" (prisoners) are deprived of due process, trial by jury, and
are subject to cruel and unusual punishment (forced drugging, solitary
confinement) and indefinite imprisonment. This in itself is psychologically
damaging and further exacerbates the issue.
If a person hurts someone, they should stand trial but until then they should
be allowed their inalienable rights.
~~~
rtkwe
The constitution doesn't guarantee/require a trial by jury outside of criminal
cases. Since involuntary commitment is not a criminal case it only requires
due process which is simply a normalized legal framework. For commitment
there's hearings with judges and legal council for the patient which meets the
requirements the Supreme Court has laid out.
~~~
wu-ikkyu
After rereading the bill of rights I see your point, though it still seems
like a very nuanced loophole that can and has been used to supralegally
imprison and abuse social deviants (i.e. political dissidents in the USSR,
marijuana smokers in the US).
1\. create a new classification of crime outside of normal criminal law (i.e.
thought crime, racial impurity, religious heresy)
2\. Streamline subjugation of undesireables by skirting the bureaucratic
barriers of criminal law system
3\. Profit
~~~
rtkwe
Well yeah, the constitution is far from airtight and largely relies on the
courts to fairly uphold the spirit of many of the clauses rather than a strict
word by word meaning. And it's a fair way to write the founding document of a
nation because it's impossible to codify every little case in a way that's not
fatally brittle within 50 years.
(PS: Imprisoning people for smoking pot isn't a good example here because it
goes through the normal criminal system. And examples from outside the US are
practically useless because so many rights and powers differ between the US
and even other close govenments like the UK.)
~~~
wu-ikkyu
>PS: Imprisoning people for smoking pot isn't a good example here because it
goes through the normal criminal system.
In the 60's and 70's in the US it was not uncommon for parents to have their
children committed to asylums because they were high on marijuana (it was
called "reefer madness" after all). And even today recreational use of
marijuana is considered a mental illness according the the DSM-5.
------
hprotagonist
This is one of those situations where broad-strokes rules just don't help very
much.
>"There ought to be a new standard of care, said Ruffin, and it should include
not just temporary involuntary psychiatric and physical treatment, but long-
term case management."
This is the crux of it. Admitting people to a psych ward for an involuntary
hold is ripe for abuse. You can respect someone's autonomy (even a homeless
person with psychiatric problems' autonomy) and, at the same time, help them
not freeze to death.
It usually starts with having enough caseworkers with enough bureaucratic
leeway to build actual relationships with their clients. I don't think we're
anywhere close to that.
~~~
mabbo
> You can respect someone's autonomy (even a homeless person with psychiatric
> problems' autonomy) and, at the same time, help them not freeze to death.
Can you? Look, the crux of mental illness is that the organ you use to
understand the world and comprehend situations and consequences is broken. If
I'm mentally ill, you can't convince me that I'm wrong or that I'm ill anymore
than someone with liver disease can process alcohol. That organ doesn't do the
job correctly anymore. Logic doesn't apply anymore.
How can you respect my autonomy if I'm wrong about my own safety? If I say "I
don't believe the cold can harm me, because I believe there is a fire inside
me", your choices are to respect my autonomy and find me dead tomorrow morning
after the blizzard, or to not respect my autonomy and I'll be alive tomorrow.
Bring an army of caseworkers to tell me I'm wrong- it won't matter. They can
all watch me die too.
Edit: to be clear, I'm talking about the most extreme forms of mental illness,
the absolute limit. Like a good unit test, always check the extreme examples
to see if your solution works.
~~~
dangerlibrary
You are describing an extreme form of mental illness that is not as common as
more treatable / manageable forms. If all "mentally ill" people were as
incapable of cognition as you suggest, psychology and psychiatry would be very
sad, hopeless professions.
~~~
got2surf
True, but in the article, both Partovi and Ruffin cite examples of clients who
"claim they own a house, or that a relative will show up any day now", despite
being injured/homeless/exposed.
To me at least, it seems logical that a reasonable person would choose shelter
over being outdoors and injured for 15 years. Making that choice is their
right, but let's address their mental health problems first to give them the
autonomy to make that choice.
~~~
galdosdi
Yes, but you and the grandparent commenter seem to treat it as black and white
-- either they are sane, or ALL logic has gone out the window. Many (most?)
actual mentally ill are not like that (spoken from first and secondhand
experience) -- SOME logic has gone out the window, and there is room to
"negotiate" or "convince" in alternate ways. But that requires getting to know
them, caring, spending enough time to earn some trust and understand more what
kind of entreaty would most appeal to them.
A good comparison is a young child (or an elderly person slowly getting
senile)! They often believe silly things, but it's not all or nothing. It's
possible to "reason" with them, but it takes more effort, time, and care,
that's all.
------
tiku
Here in the Netherlands we let them live amongst normal people, we then wait
untill they stab someone or set their house on fire, because then it is clear
they are a danger for society. Oh, and because of cutbacks the government
demands that these people pay some cash for their own pills, but these people
often don't have a lot of money, so the problem solves itself. Just don't live
next to them.
~~~
throwasehasdwi
The best solution to a homeless problem is to move them somewhere else and
make your location less attractive. You can't cure the homeless and crazy and
trying to a waste of money. Either put them back in mental wards or accept
that they're going to live on the streets and put them somewhere they won't
bother anyone.
I have a relative that's homeless and mentally ill and there's absolutely
nothing you can do to keep them off the streets. Even with a free place to
live he gets kicked out for threatening neighbors or screaming gibberish. Has
a criminal record of doing crazy stuff so shelters will give him food but will
not let him stay there.
I think anyone that's spent a lot of their life trying to help someone with
severe mental illness realizes that the only humane way to deal with these
people is to put them in a ward or prison. It's honestly much safer for them
there, they get reliable food and some medical care. These types of people are
a danger to themselves and being in a controlled environment is the best you
can hope for.
I'm personally pleased whenever I hear that my relative is back in jail
because then I don't have to worry that he's dying on the side of the road.
Since all the bleeding hearts that haven't dealt with someone in this state
keep voting to close down mental wards these people are now flooding the
streets, terrorizing people, and dying constantly.
If people don't want mental wards, which is by far the best solution, the
alternative becomes putting them on some kind of "homeless island" where they
can hurt themselves and each-other but at least not the rest of society.
~~~
jdbernard
To all of the those who have down-voted this comment, please engage in dialog
and don't just down-vote. _throwasehasdwi_ is speaking from personal
experience, directly to the question being discussed. If you do not like
either of his solutions, what would you advocate instead? Is the status quo of
persistent homeless acceptable in your eyes?
~~~
throwasehasdwi
It's still positive karma but barely. Honestly anybody that says you can
"cure" or "treat" the homeless has never dealt with them. In a wealthy society
like most western countries you don't stay homeless for long unless you're too
crazy to work.
The best way is to put them back into the mental hospitals where it's safe and
they can be cared for. I watched as my relative's old parents fought the state
like hell for years to get him committed to the last remaining indefinite-stay
mental ward in the state. The alternative was certainly death once they're too
old to keep searching for him and bringing him back home (he runs away
eventually, or occasionally steals the keys and drives).
Some of these homeless people are so mentally unstable it affects their
survival instincts. Like they don't think they need a jacket in -20 weather
one day because they saw God this morning and he's going to protect them. And
getting someone like this to take their medicine reliably? You've gotta be
joking.
~~~
Nomentatus
Don't discount too ill to work. Especially if a diagnosis has been missed
which is very common. Although these homeless people are more likely to be
rescued in one way or another, in time.
~~~
throwasehasdwi
I don't think those too ill to work are homeless for very long. They either
find a way to get medical treatment or, most likely(in the US at least) just
die.
------
dilap
> “treatment is a right,” and that “to withhold treatment is cruel.”
That's quite the Orwellian double-speak for incarcerating & drugging people
against their will.
~~~
Datenstrom
I agree but I have a close family member who has been struggling with
something similar her whole life. Luckily between disability and family she
has never been homeless but for about three decades she was only part time
living in reality. It would take getting arrested for making a scene somewhere
and court ordered back on medication for her to come back. Luckily she has
been doing awesome for long time now, even holding a volunteer job, not sure
what the change was. If she was never court ordered I don't think she would
have ever came back.
Then again I'm not sure who can be trusted to decide if someone is making
decisions based on reality or fantasy.
~~~
throwaway7767
As a counter-anecdote, I know a mentally ill person (mostly functional,
luckily, but he gets paranoid delusions during the worst times). His family
pressed the doctors hard to have him involuntarily committed one time since he
refused to go. From what I can tell, the primary effect of that is that he now
has an intense distrust of doctors and those family members, and it would be a
lot harder for doctors to help him now, even if they tried to approach him
with more empathy.
The only people now who can sometimes talk him down when he's having problems
are me and a couple of other family members that did not participate in
pushing for involuntary committal.
------
bannisterp
I live right in the middle of a hotspot for "street people" in SF. I struggle
internally with this question daily, because I see many mentally ill people
roaming the streets just outside my apartment. I've run the whole gamut of
solutions and emotions for the past 5 years, and I can only come to this
solution: let them refuse treatment, but make living on the street the least
viable option for them.
I know deep down there isn't much that can be done without incarcerating them,
but I also know that taking someone's freedom without proper cause is worse
than letting them possibly die by their own choice. There's too much potential
to abuse power that let's you lock up someone who is, by and large, law-
abiding but mentally disturbed. The hair splitting is dangerous.
That being said, in short order I will likely move to a location in SF where I
don't have to see this tragedy play out day to day. If I can't help, and I
don't like the current solution, at least I can avoid the situation
altogether.
------
1_2__3
This has always stuck with me. When I was a lot younger, in the early 90s I
was dating a guy who was pretty high up in Washington state's DSHS. I remember
him saying that massive cutbacks were forcing all the institutions they had
left to close. I asked him naively what the plan was for everyone who was
going to be released and he said "Nothing. There is no plan. There're just
going to live on the streets."
I was aghast and assumed he had to be wrong somehow. Fast forward ten years
and downtown Seattle is full of homeless people. Fast forward to today and
multiple cities are basically overrun with them, when the population of them
was tiny just 20 years ago.
I hate feeling old and partisan but my personal experience leads me to believe
this is the crazy GOP policies of the 80s coming home to roost. It's certainly
the most likely explanation given what I know and doesn't require some of the
mental backflips necessary for other explanations.
~~~
Nomentatus
I remember around then being a policy analyst for the Mental Health department
of a government and being told (from above) that lots of money would be made
available for services in the community once institutions were closed - but
knowing perfectly well that it was a bald-faced lie at the time, given which
political party was in charge, and their record. As one example, the Social
Services manual at the time made it a firing offence to reveal to a client the
existence of an available service or entitlement that the client didn't
already know about. In print. Or to publish any part of the (quite official)
manual.
------
Fricken
Nature doesn't deal everyone the same hand. Society says we should all be
treated equally. The laws of nature are absolute. The laws of society are made
up, and exist only in our minds. The mentally ill and chronically homeless
really bring out the dissonance between these two systems. We can exasperate
ourselves and flounder about helplessly. We can leave these broken people on
the street. We can round them up and put them in a junkyard, out of sight and
out of mind. Or we can pretend we can fix them up and get them working again,
even though we can't. About once a week or so the solutionists of HN go
through this routine.
------
Kattywumpus
You mean, "What should the state do?" That's a different question than what
ordinary human beings should do.
The notion that someone who said, "Jesus wants me to live on the street,"
would suddenly find themselves incarcerated and drugged to change their mind
is such a terrifying overreach of state power that it boggles the mind.
~~~
jdbernard
First, I agree with you. Making a policy of judging (often poorly) the state
of mind of other people and then forcibly stripping them of their rights based
on that decision is a dark road.
But, what do we do when that person changes from "Jesus wants me to live on
the street" to "Jesus told me to purify people wearing blue?" Or maybe a less
extreme version, "I have been commanded to anoint your car by defecating on
it." What is our responsibility as a society to those who through no fault of
their own become delusional and dysfunctional to the point where they become
abusive towards others? What agent should be charged with this responsibility
if not the government?
I don't have a good solution myself. I've just seen the damage mental illness
can cause, and it usually isn't limited to the person who is ill. I've had the
difficult conversation: "I know they're stalking you, and I know they have a
CHL, and I know they are no longer in their right mind, but there are no
authorities that can actually do anything until after they directly threaten
you in a way that you can prove."
------
meri_dian
>"Celina Alvarez, executive director of the nonprofit Housing Works, said the
group needs to make clear that it has no intention of abusing the rights of
those with a mental illness or rewriting the law governing involuntary
treatment"
Those with a mental illness are in this case unable to help themselves. It
controls them. It's the illness that prevents them from getting help. They may
refuse medical care but that's the illness talking.
By not committing them to 'involuntary' hospitalization the state is allowing
mental illness to slowly kill the suffering homeless population out on the
street.
~~~
colechristensen
This is a difficult avenue to walk because it's not very hard to define
everyone not doing what you think is right as mentally ill and no longer
deserving rights or choice. (see about half of dystopic science fiction)
~~~
JumpCrisscross
> _see about half of dystopic science fiction_
See Alan Turing.
------
marojejian
Better data would dramatically improve this situation:
\- Statistical data on who is homeless and why \- Data on how a given person's
homeless life tends to proceed over time \- Data from homeless people on how
they view their lives + their "satisfaction" (whether they are mentally ill or
not" \- Data that attempts to predict health / satisfaction in the future from
past circumstances
I'm sure some exists... but I don't hear much about it.
The article points to the value of data, by indicating that compiling a
consistent history (across service providers) of a homeless person's history
can make it very clear when someone is in the (extreme) case that they are not
going to take good care of themselves in the future.
The (wonderful) discussion on this post goes through all the complexity of
balancing respecting autonomy with promoting well-being. But even the best
comments are anecdotes. I don't know if the greater evil (today) would be a)
allowing people to destroy themselves or b) imprisoning them in a bureaucracy.
Understanding with data (top down overall + longitudinally) could give a sense
for where the common cases are, and what cases we consider are very rare.
In criminal justice, we imprison innocent people. It sucks, and we will try to
minimize it, attempting to "let 10 guilty people go free vs. convicting one
innocent" But we don't go so far as to imprison almost no one.
By analogy, with better data, I would feel more empowered to have an opinion
of what direction to push in here.
------
notliketherest
For the truly mentally ill, reopen the institutions, where they will be safe
from harming themselves and others. This will drive down costs tremendously on
these cities that suffer from chronic homelessness. Have we got away from that
whole 1960s, "One Flew Over the Cookoos Nest" notion that mental institutions
are nothing more than jails and that these people are just following their own
"movies" and just need to be "let free"? These are sick people that need
shelter and help and cannot do it themselves.
~~~
pyre
While many of these people need help, the institutions were closed because
they were rife with abuse. It's a playground for predators. If their victims
attempt to speak up, you have the choice between believing the "sane" person
or the person that is so mentally disabled that they need to be in an
institution.
> These are sick people that need shelter and help
There is a large amount of literature on how said institutions didn't provide
much help other than sedating people and subjecting them to procedures like
lobotomy for diagnosis such as "mild" as depression.
------
joshuaheard
They need to change the legal standard for involuntary commitment to a psych
ward. At present, the standard is that as long as the patient is not a danger
to others, they are allowed to roam the streets at will. I think a better
standard is to broaden it to where if they can't take care of themselves, they
can be involuntarily committed. That used to be called "vagrancy" and was a
crime. I would find some middle road where it is not a crime, but a civil
order.
~~~
nickpinkston
If they're not a danger to others why not allow them to do what they want? So
you can be more comfortable?
~~~
jdbernard
In my experience it's very hard to prove to the standard required for the
authorities to intervene. Basically you have to wait until they have already
hurt someone before action can be taken. And it's even worse if they are only
a danger to themselves. Worse still if they are simply incapable of sustaining
themselves rather than actively suicidal.
Believe it or not many of these people have relatives and friends who _do_
care about them, deeply, but are powerless to help them because in their
delusions they have violently rejected their help. I've watched a friend of
mine starve nearly to point of death on the street and be unable to do
anything to help him other than take him to lunch whenever I could.
------
bbunix
The key here is "refusing help". In the US it's pretty well one of our basic
rights unless we're a danger to ourselves or others. There are really only 2
choices, establish enough trust to encourage the person to receive help, or
wait until their behavior violates the law, at which point they've forfeited
certain rights and treatment of some kind can be mandated.
This process has mostly been used on addicts and alcoholics (treatment or
jail, drug courts), and sometimes works.
Here in Key West, you can also get a bus ticket somewhere else, presumably
where the person has more of a support system (family, friends)... if you
agree not to return. This solves the problem for Key West, anyhow :)
------
vondur
I'm noticing here in California, many of the mentally ill homeless simply
ended up in jail, where they are given some level of care. However, with the
recent mandated Federal court order to reduce the prison population, there has
been a flood of them back on the streets. I'm also going to speculate that
many of the mentally ill also have drug dependency issues.
------
Qantourisc
The choice here is (maybe there is a grey-scale here, but I don't see it):
either you accept oppression and forcibly commit them (under certain
conditions), or you value freedom and let them be if they choice to. The only
general consensus seems to be: when they don't break any laws (or endanger
other people).
------
rbcgerard
It's always hard to judge the way people will certainly abuse a new authority
over their fellow man
------
fpgaminer
One of my friends was mentally ill. I had known him for years, but never knew
about the illness. It wasn't until a cataclysmic event which resulted his
suicide that I gained first hand experience with ... the tragedy of these
broken minds.
He was an incredibly intelligent and accomplished person, but, like all of us,
had his demon. For him, it was robo-tripping; taking large doses of cough
syrup to get a high. It had been going on for years, maybe even decades. The
years of abuse manifested as a hidden mental illness; he had concocted an
imaginary friend who he could visit whenever he was tripping. The two of them
grew very close together. The relationship was complex, as was this imaginary
person. For all intents and purposes it was another "intelligence" living
inside him.
Eventually he tried to cut his "addiction". But when he tried to stop cold
turkey, he realized not taking the drug anymore would mean never seeing his
friend again. By this point, he had grown too attached. So he continued his
now ritualistic highs.
One day he was taken to the hospital for attempted suicide. Amidst all of this
was an underlying chronic depression. The depression predated the abuse,
likely your classic case of the depressed genius. He was released very
quickly, I think within 24 hours or so. But now more of his close friends,
including myself, knew something was up. I had no idea any of the
aforementioned abuse was going on, nor the extent of his depression (I knew he
suffered, but didn't know it was bad).
After that event, he sat down with me and told me everything. It was a long,
shocking conversation. The evening after was one of those cold nights you
don't think you'll ever escape from. Like being lost at sea. At one point he
showed me a bag. It was filled with pills; gel capsule cough syrup pills.
Probably about two fists' worth of the stuff. He said that was his dose for
later; the kind of dose he always takes.
I didn't say much. What could I say? He talked about everything; the drug, his
friend, the hospitalization. When it was all over all I could do was hug him
and tell him I was always there for him if he needed. He wasn't the kind of
friend I hugged; we were more intellectual buddies. In fact, that may have
been the only time I've hugged him. But, I think, despite my mind whirling
from everything I had just heard, somewhere deep inside I knew ... this might
be the end.
The next few days were tense. Our mutual friends talked over what to do; we
began seeking advice on how we could get him help. Could we "commit" him to
get mental help? By this point, he didn't want help.
During the long conversation with him, he talked about the hospitalization.
How violated he felt by the event; being forcefully taken, poked, prodded,
drugged, and held against his will. In many ways I had looked up to his man;
he was older and smarter than me. So when I racked my brain thinking about
whether we should force him to get treatment ... I just didn't know what was
right.
When he wasn't under the influence, he was more or less normal. And if he did
get treatment, he would lose his imaginary friend. I know that sounds weird. I
could never describe this "imaginary" person the way my friend told it to me.
But, you know how someone will be telling you about a person they've been
hanging out with, and just by the way they talk and the look in their eyes you
know they're in love (but don't realize it)? It was kinda like that.
So I could see his position. If he felt that strongly about this "illusion",
how could I forcefully take it away from him?
It was only a few days before everything was over. He committed suicide. We
didn't get him help in time.
I'm still not sure how I feel. Should we have more aggressively sought to
force help upon him? Should I have said something during that long confession
of his; protest his actions, tell him to get help ... or ... something?
And in general, what should you do when anyone is in a position like this?
Clearly mentally ill, but so delusional that they don't want help ... what is
the right move? Should we force help on them, like this article discusses? My
friend's case would have been a little easier; he was a danger to himself. But
I don't think the situation is any more clear cut.
I just wanted to share my story. I don't know if many people have had to face
this kind of stuff first hand; had to make these kinds of choices. Or, at
least, I hope most haven't had to. It's been many years since it all happened.
I still cry sometimes when I think about it. I don't envy the workers who go
out in the streets and try to help the lost and the homeless.
~~~
raphlinus
Thank you for sharing the story of your friend. It brought tears to my eyes.
Feeling guilt about not being able to do more is a natural consequence of
suicide. But it sounds like you were there for him, able to really listen.
Think of how many people struggling with these sorts of problems don't have
that.
------
known
Call 911
------
19eightyfour
To be honest, when I have a lot of money, I want to build housing for homeless
people, but there's a difference. They work for us. There's a product that any
human can do. We have a couple of floors full of cubicles with terminals. And
in exchange for doing X hours of work for Y days per week using this product,
a person gets their own room, 3 meals a day at the canteen, and some kind of
monetary / card / bitcoin allowance they can use in the outside world. The
housing has its own in house security, with monitoring and accountability.
Also we vet and include some sort of community building, personality building,
NGO / social welfare programs to work with people. It's sort of like an 18th
century work house. Without the shame, coercion or slavery aspects.
A very important point is we do not start from the perspective that "these
people are 'wrong' and need to be 'fixed'" instead we start from the lovely
awesome assumption that these people are humans and are inherently useful. So
we get them to do useful things and give them stuff that most people want.
Obviously, some people don't want to be part of any community, and some people
would still prefer to live on the street even if they have housing. Such
people can work there, but the whole package is really a niche for people who
are looking for the whole package.
Basically: food, shelter, work, money, without any hassle at all.
~~~
hashkb
You have good intentions but need to learn more about how one finds themselves
in chronic homelessness first.
If you are expecting something in return, or holding over someone (who may be
delusional) a condition for help, you will not end up helping the people you
set out to.
~~~
19eightyfour
I think it's fair to expect something in return. As long as the terms are such
that suit the people, they'll be part of it. These people survive on their
wits and customs of the street. They're not as hopeless as perhaps is made
out. My idea is to redirect their energy and resourcefulness towards something
useful, and add some socialization and boundaries that help them interface
more fruitfully with normal civilization. But importantly, as a first step,
doing useful work in exchange for things they need.
| {
"pile_set_name": "HackerNews"
} |
Meet the Napster (2000) - mrduncan
http://www.time.com/time/printout/0,8816,998068,00.html
======
zanek
Good article from way back. Wow, I'm surprised Fanning only had 8% of Napster
by the time Napster was sued. Anyone know if he is a millionaire ?
~~~
yoseph
I think he is now.
[http://techcrunch.com/2008/05/08/shawn-fanning-finally-
gets-...](http://techcrunch.com/2008/05/08/shawn-fanning-finally-gets-a-real-
payday-electronic-arts-buys-rupture-for-30-million/)
| {
"pile_set_name": "HackerNews"
} |
The Cost of Losing a Developer - nickb
http://david-carr.blogspot.com/2007/08/cost-of-losing-developer.html
======
palish
It seems like quantifying the loss of a developer in terms of dollar value is
pretty futile. That value is volatile from company to company.
One thing we can _try_ to do is measure the skill difference between two
programmers. This is a hard problem, but if we assume that some percentage of
their checkins are new features, some percentage are bug fixes, and so on..
Perhaps even going through and manually tagging each changelist (have a
convention to prefix a changelist with BUG: or FEATURE:), then we have a sort
of rough statistical model of their performance.
So now we have two categories, _bug fix_ and _new feature_. (I'm grouping
refactoring into bug fixes for now.) Their performance in each category can be
measured by (number_of_changelists / time). This assumes a perfect world,
where each bug fix doesn't introduce new bugs, and each feature doesn't add
any new bugs. These totally contradict one another, so we can tweak some
parameters, perhaps introducing a percentage chance that one of their
changelists will introduce a bug, which counts against their productivity
score. (You can do some more interesting statistical analysis here at the
sourcecode level to determine who's bug was fixed, and actually measure how
often they produce bugs.)
But wait a second, what's the value for 'time'? It could be their whole stay
at the company. But what if we change it to be, say, a week? Now we can get a
velocity value by doing productivity(t) - productivity(t-1).
Those two metrics combined are pretty useful to measure a programmer. You have
their productivity over a time value, and you have their velocity based on
previous producitivity values.
Now we apply it to the whole company. Add up everyone's productivity for the
week and you get the current company productivity. Subtract that with
everyone's productivity for the last week and you get the company's
productivity velocity. To measure how each of them would affect the company if
they left, subtract out their productivity from the equation and compare that
with them in the equation.
If your productivity score includes how often you produce bugs, you can
actually measure who is hurting productivity more than they're helping it.
However, each bug is of a different magnitude, so that number is bogus until
you can measure the complexity of each bug.
The one thing this system does _not_ take into account is information lost
because only that person knew that information. That's a very valuable asset
and nearly impossible to measure. So the best way to account for that is to
increase a programmer's productivity velocity over time. You can assume that
if they're setting out to accomplish something, whether it's a new bug fix or
a new feature, they will accomplish it in less time if they start working on
it 10 years on the job versus one day on the job.
Also, someone (perhaps the project leader) needs to put a weight for each
changelist. The weight measures how valuable the new feature was, or how much
value was added by fixing a bug. This has to be done by someone other than the
developer, because they'd have an incentive to lie.
This seems to work, because if you have a superstar leave after one day with
the company, it doesn't hurt the company at all. Whereas if he leaves after
ten years with the company, not only will the company's absolute productivity
go down, but the velocity will take a hit for the next month or so too.
All in all, it seems pretty hard to accurately measure a programmer's value,
so I say screw it. Humans are great at recognizing patterns. The whole team
should be able to recognize that Bob isn't pulling his weight or is under-
motivated, and either give him extra vacation or reassign him to a sister
company. Plus if the programmers ever found out they were being measured, the
company's productivity would drop like Wile E Coyote. This sort of analysis
should really only be applied after a programmer has left or if the company
has made the affirmative decision to fire them (possibly to reestimate
schedules), not as an ongoing thing.
This is something I came up with off the top of my head just now, so it's
probably totally wrong. More research into this field would be really
interesting, because if we can measure productivity for a programmer, one
could measure the global productivity scores for all programmers. Somehow, I
think a certain company that starts with a Y and ends with an R that would be
really interested in that.
New startup idea? I'm too busy with mine, go for it. Businesses might pay
oodles if you manage to measure programmer productivity accurately (or give
the impression that you are).
------
ivankirigin
There is such a thing as "negative people". Folks that cost more in correcting
their mistakes than in contributing to a problem. This often happens with
anemic partnerships.
The cost of losing someone largely depends on how good and useful they were.
It is so case-by-case that such a list is useless.
| {
"pile_set_name": "HackerNews"
} |
On Open-Sourcing Libraries - couac
http://williamdurand.fr/2013/07/04/on-open-sourcing-libraries/
======
antoncohen
I would like to add that when open sourcing a library, meaning software
designed to be included within or used by other applications, please don't
license it under the GPL. Of course you can license it under whatever you
want, it's your code, but you need to understand the consequences. If the
library is GPL it can only be used by other GPL applications (if the
application is distributed), which excludes major open source projects like
Rails (MIT) and Django (BSD). It seriously limits amount of people that can
use your library, and hopefully you are open sourcing a library because you
want to help as many people as possible.
Even the LGPL doesn't make sense for interpreted languages or compiled
languages that don't link like C. The wording of the LGPL is pretty ambiguous
when it comes to languages that 'include' libraries into their code instead of
linking against complied libraries. FSF argues it's not ambiguous [1], but
that fact that they even have to make that argument proves it is. As the
original author of Twisted Python wrote "It would be a halfway accurate
statement that I selected the LGPL exactly because it doesn't make any sense."
[2] Twisted is now MIT licensed
[1] [https://www.gnu.org/licenses/lgpl-
java.html](https://www.gnu.org/licenses/lgpl-java.html)
[2] [https://twistedmatrix.com/pipermail/twisted-
python/2004-May/...](https://twistedmatrix.com/pipermail/twisted-
python/2004-May/007946.html)
~~~
shizzy0
> It seriously limits amount of people that can use your library
Yes, it does seriously limit the amount of people that can use your library--
without giving anything back.
> hopefully you are open sourcing a library because you want to help as many
> people as possible.
Help as many people as possible do what? Get rich by composing together a
bunch of liberally licensed software to do a task and then close sourcing it.
No, thank you.
I see licensing as a Hawk-Dove-Retaliator game[1] for modeling resource
competition. Each kind behaves differently: The Dove never fights and always
flees. The Hawk always attacks and never flees. The Retaliator only attacks if
attacked. Pay off matrices describe in detail how well each kind does against
the other. Dove vs. Dove both do well; they share. Hawk vs. Dove, the Hawk
wins everything. Hawk vs. Hawk, the beat each other up; both lose. Retaliator
vs. Dove, just like Dove vs. Dove. Retaliator vs. Hawk, like Hawk vs. Hawk.
My analogy is this: The BSD licensor is a Dove, the proprietary licensor is a
Hawk, and the GPL licensor is a Retaliator. If you want to be nice but make
yourself vulnerable to exploitation, be a Dove; Doves like Doves, and Hawks
love Doves--it's popular. If you want to get rich, then exploit all the Doves
and be a Hawk; Doves worked hard, so you don't have to. If you want to have
your work respected rather than exploited, be a Retaliator: happy to cooperate
with those who cooperate, but willing to punish those who defect and refuse to
cooperate. Which of these strategies is stable in the long-term? See the links
below for a more detailed answer, but Doves certainly aren't.
Doves may enjoy a wonderful period of peace and cooperation, but they're so
easily exploited that it makes one wonder how long it will last. In a
population of Doves, it's best to be a Hawk. However, a population of pure
Hawks does terribly. A population of Retaliators though is nearly immune from
invasion.
Note: There are many salient differences between licensing and this animal
behavior model. I don't contend that it is a perfect analogy, but I think it
is worthwhile for considering long term trends.
[1]: [http://en.wikipedia.org/wiki/Chicken_(game)#Hawk-
Dove](http://en.wikipedia.org/wiki/Chicken_\(game\)#Hawk-Dove) [1]:
[http://www.oocities.org/hawkdovegame/strategies.htm](http://www.oocities.org/hawkdovegame/strategies.htm)
~~~
tjr
See also:
[http://zedshaw.com/essays/why_i_gpl.html](http://zedshaw.com/essays/why_i_gpl.html)
------
eksith
I've been racking my brain trying to come up with a basic, concise readme to
include with my code as well as a cabin design I've been working on. At first
glance, these are wildly differing things, so one license type E.G. creative
commons had too many options.
Finally, I came up with one single readme file I can include in almost all my
work (except where I have to combine other stuff under different licenses).
It's basically a variant of the ISC license.
Feel free to use this for whatever...
Introduction...
Things your whatchamacallit does
___________________________________________________________________________
README
Important stuff about the project.
Requirements, preconditions, defaults etc...
___________________________________________________________________________
CONTACT
Twitter : @eksith
Website : http://eksith.com
Email : Eksith Rodrigo <reksith at gmail dot com>
___________________________________________________________________________
COPYING / LICENSE
The contents of this package are licensed under the following unless
otherwise noted.
Copyright (c) $YEAR, Eksith Rodrigo
Sources, libraries, binaries, diagrams and/or images and documentation
included with this package are hereby referred to as "materials".
Permission to use, copy, modify, and/or distribute these materials for
any purpose with or without fee is hereby granted, provided that the
above copyright notice and this permission notice be included in all copies
in an applicable and appropriate format.
THESE MATERIALS ARE PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
WARRANTIES WITH REGARD TO THESE MATERIALS INCLUDING ALL IMPLIED WARRANTIES
OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR
IN CONNECTION WITH THE USE OR PERFORMANCE OF THESE MATERIALS.
END.
------
mwfunk
I would add, please use a known and widely-used license (IMO, preferably a
2-clause BSDL variant or LGPLv2, depending on your attitude towards derived
works). Don't make up your own or just state that it's public domain. Public
domain is actually not a well-defined concept internationally, and means
different things in different countries.
~~~
yoklov
[http://creativecommons.org/choose/zero/](http://creativecommons.org/choose/zero/)
is a good alternative/method to releasing into the public domain, and is (to
my knowledge, IANAL) unambiguous internationally.
~~~
kibibu
[http://www.wtfpl.net/](http://www.wtfpl.net/) is pretty cool too, if only
because any court transcripts involving disputes would be pretty hilarious.
------
alexchamberlain
The most important thing on that list is the Licence. No licence and most
people can't use it.
~~~
freework
Its becoming less of an issue as more and more as software migrates to being
"as a service". A webapp is not distributed, so the license doesn't matter at
all.
~~~
alexchamberlain
Errrr I present AGPL
------
zalew
he didn't mention the most important - write the docs
[http://www.youtube.com/watch?feature=player_embedded&v=KEakc...](http://www.youtube.com/watch?feature=player_embedded&v=KEakc8r4r7M)
------
jorgecastillo
I will make a small off-topic question. I really like the ISC license but for
a small snippet of code I think that it's still to big. I choped some parts
and got it to this:
Copyright (c) 4-digit year, Company or Person's Name
Permission to use, copy, modify, and/or distribute this software for any
purpose is hereby granted.
THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
REGARD TO THIS SOFTWARE.
Would this be a valid open source license?
I am not using this license for anything big. Most of my code is pretty much
useless and for the code I consider more useful I use the ISC license.
~~~
rogerbinns
It is generally a bad idea to make your own, since you won't be aware of
international issues. Similarly since your license is non-standard, anyone
using the code now has to a do legal review to make sure things are ok,
instead of looking in their list of standard approved ones.
Pick one from the top of
[http://opensource.org/licenses](http://opensource.org/licenses) At the bottom
of my LICENSE file I add "Alternatively you may strike the license above and
use it under any OSI approved open source license such as those listed at
[http://opensource.org/licenses/alphabetical"](http://opensource.org/licenses/alphabetical")
See also
[http://creativecommons.org/choose/](http://creativecommons.org/choose/)
although they are rarely used for code.
------
_sabe_
I think it's interesting that in this time of fancy collaborative tools like
github, the trend no longer seems to be collaboration but to reinvent
everything as a "one man show". And it becomes apparent with new technologies
like Go and redis where there are like 10 different implementations of the
same database libraries at any given time, but they are all gone within a
month...
~~~
couac
Yes, because things are easier than ever for people that want to contribute
but also for those who want to create new projects. Maybe GitHub could suggest
existing projects to contribute on before creating a new repository :)
------
dakimov
Platforms.
| {
"pile_set_name": "HackerNews"
} |
It will take a 'baby elephant' to knock over this bike [video] - ZeljkoS
http://news.bbc.co.uk/2/hi/programmes/click_online/9776325.stm
======
Irregardless
> One of the most common accidents for motorcyclists is falling while turning
> a corner.
Yes, due to loss of traction or excessive cornering speed. But those are both
issues inherent to two-wheeled vehicles, and adding gyroscopes won't solve
either.
So you gain the ability to ride in the rain without wearing rain gear, but you
give up cargo space and visibility. Not to mention the fact that your head
will now be in the perfect position to get rammed by a bumper, and the lower
profile increases the likelihood that other drivers won't see you.
It's a nifty trick, but I don't see who this would appeal to. Most
motorcyclists already have rain-proof gear, and non-motorcyclists will still
think it's a death trap.
~~~
imglorp
I'll address the possible appeal as a diehard daily motorcycle commuter; from
110f down to 20f, anything except ice and snow.
I invested in a decent sport touring bike with ABS and heated grips, plus
riding gear. Yes it's warm and dry. There is some irritation where it takes a
few minutes to put on all the gear (pants, boots, jacket, gloves, ear plugs,
neck gator if cold, and helmet) over work clothes, take them off at work,
repeat on the way home. Cargo can be an irritation, needing tying down. A bag
of groceries or case of cans is okay but not much more. I need a better way to
carry a laptop. Yes, I dropped the bike once, sudden braking at a stop sign.
Yes, it's pretty common.
So an enclosed gyro vehicle would improve these issues for me: convenience and
cargo. The tippy thing is a minor plus.
The downside: it takes away most of the fun of a bike. The fun is hard to
qualify but it involves being outside, connected to the machine, shifting,
leaning, braking, and in general micromanaging your outcome.
Am I likely to get one as a commuter? Maybe. A Miyata or Mini would fill a
similar bill and buy more utility.
~~~
syntax-rules
At least it still leans the right way! I think a big part of their pitch was
fuel efficiency too, in theory you can get the weight pretty low, although
you'll still be in goldwing territory. Also, hard luggage helps a bit on the
bike too, but I still spend all winter getting dressed.
------
chimere
This actually uses control moment gyroscopes [1] in a scissored-pair
configuration, the subject of my undergrad thesis. These differ from standard
gyroscopes in that they are gimballed to produce a reaction torque. They are
actually most commonly used on large spacecraft for attitude control, so the
comment about "technology from the ISS" is quite relevant.
However, the statement that there are "two for redundancy" is dubious. The
torque from a control moment gyro is not produced in a constant vector - the
torque vector rotates with the gyroscope as it is gimballed. Thus, if there
was only one gyro, some component of its output torque would be aligned with
the yaw axis, which would create some rather unpleasant and dangerous effects.
The scissored-pair configuration is required to cancel out the yaw torque.
[1]: <http://en.wikipedia.org/wiki/Control_moment_gyroscope>
------
majke
I can't get if they are really serious about mass-producing an electric
motorcycle. On technical side this company looks like it's run by an
individual - Daniel. Team page [1] shows 6 employees not named as "Advisors".
Out of who only two are technical (Daniel, the CTO and Kevin).
More worryingly Kevin's linkedin page shows he's not working at Lit Motors for
last two months.
Looks like on technical side Daniel is pretty much alone. It's not necessarily
bad, maybe they are just starting. I'm just worried they'll disappear.
Does anyone know if they are funded?
[1] <http://litmotors.com/lit-team/>
------
jentulman
Off topic rant, the BBC's Click strand drives me up the wall on occasions that
I see any of it. We used to have the wonderful (if haphazard) Tomorrows World
as primetime science viewing and now we're left with Click which is broadcast
in a time slot for the terminally stoned and apparently produced by ex '...
for dummies' editors. And don't get me started on the abysmal Gadget Show.
~~~
coob
I think you're viewing Tomorrow's World via rose tinted glasses. I loved it as
a kid but if you watch an old episode now you're guaranteed to cringe.
~~~
jentulman
I'm sure I am, but unless I'm remembering it very badly they didn't have quite
the same 'OMG Science!' presentation.
The bit about the gyros in the Click video is awful. I was expecting her to
use the word boffin at any moment.
~~~
hnriot
I was expecting (hoping) to see a baby elephant :)
------
Shivetya
Enclosed two wheelers do solve the problems of, its too hot, too cold, to wet,
and more. Yet the price point isn't sufficient to get me or many others out of
cars let alone off of motorcycles.
Twenty four thousand is definitely out there but even twelve thousand will
price it beyond the means of many. Many used bikes if not cars will fall under
that price and unless gas is just astronomical it becomes a bit hard to
justify its purchase. Its a great idea, don't get me wrong. However compared
to existing transportation options its very pricey.
Safety wise, with good use of LED lighting one could make it stand out very
well in traffic without blinding other drivers because its a bit diminutive
for my liking.
~~~
neilmiddleton
I wouldn't be so sure. Working in GBP that bike would cost me £7K. Say I had
it three years, I'm looking at it costing £2.3K a year. Given that with my
current commuter bike (a BMW R1100RT) I already have an annual cost of £1250
in fuel alone. That's before considering all the other costs you get with
owning a bike.
Add to this that this is considerably more comfortable, more weatherproof, and
not a 10 year old like mine it seems a fair price.
~~~
Adirael
I don't think that's a fair comparison. You're speaking about a 1100cc 90hp
machine and comparing it with a small electric motor.
My commuter bike is a 250cc with 28hp. It has 9 years, carbed. Inside the city
(less than 100kph) it gets about 3.2L / 100km and 280km per tank. It's cheap
as fuck to fix and the bike itself was like 1K (used, around 3-4K new, it's
shinny).
~~~
stephenhuey
But after loads of early adopters start buying it, couldn't we expect the
price to drop a few more thousand dollars?
~~~
Adirael
Maybe, maybe not. I don't think it will ever be cheaper than a commuter bike.
More convenient of course, but not cheaper.
On most countries/states is also competing with small cars because you can't
legally lane split. Right now I've got a loaner and it's a 4 seater, a Seat
Mii. It consumes just a bit more than my bike and it's very small and cheap
(around 6-7K new, cars are expensive around here).
------
nakedrobot2
I saw this vehicle at the eg conference (www.the-eg.com) in April. I recognize
the marketing pitch - that it takes "a baby elephant to knock it over" - good
message!
I think it will take a lot for regulators approve this vehicle, because it
really is something quite new, and untested in the field. It does appear to be
fantastically safer than "normal" motorcycles, and I would love to try one
out.
What was never mentioned was how it performs on extremely slippery surfaces.
This is where two-wheeled vehicles have a lot of trouble.
Also, one complaint about the BBC article itself - it uses "technology from
the Space Station and Hubble Telescope: gyroscopes" - Really, BBC? :-)
------
bambax
Is it really called the C1? "C1" is the name of a scooter with a hard top,
distributed by BMW:
<http://en.wikipedia.org/wiki/BMW_C1>
~~~
Joeboy
<https://en.wikipedia.org/wiki/Sinclair_C5>
------
neilmiddleton
I'd like to see how this behaves with the typical things that cause a bike to
crash, for instance, the front end washing out on ice, or a locked front
wheel, or loss of traction on an accelerating rear wheel.
Highsiding this could still happen I guess.
~~~
danielparks
Seems like the gyroscopes would help with a bunch of those — traction issues
become less about keeping the bike upright and more about controlling where
the bike goes.
I don't see anything about ABS in the FAQ, but that would avoid the problems
of locked front or rear wheels.
Also, I imagine this has only one brake control, unlike a motorcycle, so you
can't lock up one wheel by stomping on your rear brake but not grabbing the
front brake.
I also wonder how effective the gyroscopes would be against a high-side crash.
Would the having to adjust for hills limit their ability to prevent one?
Having a seatbelt seems like it might help with high-sides, too.
------
redcap
The bearded guy raised the point of needing to trust the vehicle to not fall
over, and there was a lot of talk about how it looked and what kind of cool
features were included.
But before I purchased it, I'd definitely want to have a test ride to see how
it went, and perhaps some decent feedback from Top Gear - how does it really
handle in a variety of situations?
~~~
simias
I expect that even if the gyros stop while you're driving you wouldn't fall
over because... well because that's how bikes work. It might change the way it
handles though.
So I would only be worried about it falling over while stopped, which is not
as bad I guess.
Here in Paris I see a lot of those motor tricycles that don't require
motorbike license, so I think there's definitely a market for a not-so
dangerous and simpler motorbike in congested urban areas.
By the way I hate it when the hostess introduces gyros like "space age
technology". Yeah, my bike has bits of steel soldered together, you know, like
the International Space Station!
~~~
duggan
> I expect that even if the gyros stop while you're driving you wouldn't fall
> over because... well because that's how bikes work.
I don't imagine the dynamics would be the same, after all, _you're_ the gyro
on a normal bike. If the vehicle was unloaded and you were going straight,
you'd probably be able to keep enough manual balance control to come to a
relatively controlled halt deploying the parking struts.
However, I imagine the gyros are going to be compensating for internal
imbalance (shopping, baggage) in everyday scenarios, or be travelling around a
corner, or in traffic, etc, so you might have less time than you think to
regain control before toppling.
~~~
simias
Don't the wheels themselves act like gyros at medium speed? But I get your
point, losing the gyros out of the blue on the highway might create a very
dangerous situation.
~~~
barrkel
Yes they do, but the primary reason bicycles (as well as motorbikes) have
stability is because of trail - the contact point of the front wheel is behind
the steering axis.
[http://en.wikipedia.org/wiki/Bicycle_and_motorcycle_geometry...](http://en.wikipedia.org/wiki/Bicycle_and_motorcycle_geometry#Trail)
A banked-over bicycle naturally tends to turn into the corner because of
trail, and that turning-in torques the bike back towards upright - turning the
handlebars towards the centre of the curve moves the bottom of the bike
towards the centre of the curve, and that pulls the bike upright.
The larger the trail, the more stable the bike is. Sportsbikes tend to have
shorter trail so that they turn in faster, cruisers tend to have longer trails
so they are more stable on long straight roads.
Loss of gyros would be far more noticeable at low speeds (less than 20mph)
than high speeds IMO.
~~~
jdbernard
While trail and gyroscopic forces both influence steering and stability,
neither are required. It has been shown that a bike can still be self-
balancing even without trail or gyroscopic forces, though positive trail and
gyroscopic forces do make it easier to balance and more stable (see
[http://bicycle.tudelft.nl/stablebicycle/StableBicyclev34Revi...](http://bicycle.tudelft.nl/stablebicycle/StableBicyclev34Revised.pdf)).
ithkuil's comment is the more accurate description of what is going on.
~~~
barrkel
ithkuil is saying the same thing as me, in a different way. I'm talking about
how bikes are self-stable, he is talking about how bikes are stable with
active input. Trail creates a steering feedback system. You need feedback from
lean into the steering in order to create something self-stable, and trail is
the simplest way of doing that.
------
ericssmith
A motorcycle turns by 'falling over'. For me, that and the acceleration are
the main attractions. Can't imagine this will get many motorcyclists to
convert.
~~~
Adirael
Counter steering. This thing turns like a motorcycle, it's the only way
(AFAIK) to turn a two lined wheeled vehicle at speed. It's not a Can-Am.
~~~
barrkel
It has a steering wheel. Can you imagine counter-steering with a steering
wheel? Swerving to avoid something on the road? Gyros would greatly reduce
agility if they were not deeply tied into the steering, so I wonder if the
steering isn't a direct mechanical linkage.
~~~
Adirael
Not sure, maybe. I think they'll be trying to target people who likes MCs but
are too afraid to hop in one, so it would make sense to have the counter
steering mechanically done instead of giving you the full control... I also
couldn't find anything about speed and power.
------
Narretz
As a non-native speaker, "bike" confuses me. This is some sort of motorcycle
... what do you call a bike nowadays that this didn't confuse anyone else?
~~~
polymatter
bicycle = pedal powered bike motorcycle = bike with a motor scooter = bike
with a small motor
(I am UK native, but not a bike person)
------
pbhjpbhj
From the video:
"Imagine a touchscreen embedded in the steering-wheel"
Yes, imagine all the crashes it's going to cause.
~~~
zalew
reminds me of this [http://jalopnik.com/5390061/amazon-users-hack-steering-
wheel...](http://jalopnik.com/5390061/amazon-users-hack-steering-wheel-laptop-
desk-page-show-outcome-of-use)
~~~
freehunter
Hack? Really Jalopnik? You mean they uploaded pictures and reviews in exactly
the way Amazon intended, albeit in a humorous fashion to make a point?
People annoy me far too often.
~~~
zalew
yeah, meanwhile in another thread
<https://news.ycombinator.com/item?id=4904320>
------
danielparks
The FAQ is here: <http://litmotors.com/faq/>
Notably, C-1 is a code name, not the final product name.
I'm curious how the gyros interact with turning. Presumably they have a
limited ability to change orientation (necessary for say hills at the very
least). It sounds like the steering wheel is hooked to the front wheel
mechanically (from the FAQ: ”… with mechanical backups to allow the driver to
steer and stop the car even in a catastrophic failure of all systems”). Does
that mean you have to countersteer like in a motorcycle?
(<http://en.wikipedia.org/wiki/Countersteering>)
I could imagine the steering wheel manipulating the gyroscopes to initiate
leans rather than turning the front wheel. I'm unsure how effective that would
be, especially at low speeds.
EDIT: I looked at some of the videos on their website. It seems like the
steering wheel does turn the front wheel, and the gyros are free to tilt to
accommodate hills. The video shows them tilting toward each other on a lean —
I think that means they rotate in opposite directions? Not my area of
expertise.
------
merraksh
Previous discussion:
<https://news.ycombinator.com/item?id=4037645>
------
mikek
Note that he says 'baby elephant' instead of 'car'.
Edit: a baby elephant weighs 3 tons, whereas an average car weights 2 tons.
Hmm.
~~~
GigabyteCoin
Cars can carry a lot more inertia than a baby elephant.
------
prof_hobart
As a motorcyclist, I'd like the tech to be put into more traditional
motorcycle bodies. The idea of not being able to be knocked off, or fall over
on an icy road, appeals - but the look of this really doesn't. It reminds me
of the similarly named BMW C1 (<http://en.wikipedia.org/wiki/BMW_C1>).
~~~
simias
I don't think they're going for the biker market. After all, it has a steering
wheel, not bike handles. That alone hints that it probably drives somewhat
like a car.
~~~
prof_hobart
The interview suggests that they are after both markets, and this is obviously
a prototype vehicle - there's no reason why they couldn't produce both a car
replacement and a more stable motorbike as separate vehicle.
------
happywolf
A cool-looking vehicle, but wonder how much more weight it has compared to the
regular motorcycles? I think embedding a cell phone at the center of steering
wheel is a sure-fire way to distract driver attention and cause accidents.
------
anjc
Is there potential for something like this to be safer than a car during a
collision, ignoring the fact that it can stay upright? I presume that a car
going 30 miles an hour is going to have more of an impact than a baby elephant
pushing, so i don't like the idea of being enclosed in a soft shell which is
just going to fall over and go under a car.
Is it easier to fit small vehicles like this with things like roll cages, or
more encompassing air bags? Or will a car always have a safety edge because of
crumple zones etc?
~~~
timthorn
And what happens to the gyros' energy in a crash?
~~~
jdbernard
Wow, I had not even thought of that. If the integrity of the frame is
compromised during the collision that seems a very scary prospect.
------
spupy
> a bike using technology found on the International Space Station and the
> Hubble Space Telescope - gyroscopes
Holly cow, gyroscopes! The technology of space travel!
------
rmason
Does anyone know if the Lit will qualify for the US governments $7500 electric
car subsidy?
------
srlake
I hope Tesla buys them. Model-B.
------
dbz
So, you could add gyroscopes to a motorcycle and there would be no difference.
------
bmuon
Alternatively, there are some enclosed electric tricycles going around that
may have some success like the Arcimoto: <http://www.arcimoto.com/>
------
duedl0r
duh.. a guy patented this more than hundred years ago:
<http://en.wikipedia.org/wiki/Gyro_monorail>
tsss...
------
huhtenberg
And there's no chance that gyros (abruptly) stop, because... ?
(edit) OK, let's make "abruptly" optional. So what's the contingency plan for
when gyros spin down and stop?
~~~
sdoering
Well. And what when AirBags stop working, or anti traction in cars, or...
Every technology might fail. And every device will fail. And it does so in
cars, in planes, in trains or whatever.
That's why (so do I believe), they built two gyros in there. One for fail-
save-mode.
~~~
kayoone
Still if the traction system in cars fails you dont fall over and and lie on
the street immobile. They have a second one for fail safety, but i think there
could relatively easily be a case where both fail, like no energy for whatever
reason.
~~~
Xylakant
Gyros spin very fast on very efficient bearings. A rotating mass will not stop
immediately unless forced to do so. So even when power fails completely, the
gyro will continue to rotate for quite some time (several minutes probably)
and fulfill it's purpose - well, unless something penetrates the gyro housing
and blocks the spinning wheel. But then I guess your problem is not limited to
falling over.
Another issue with fast spinning disks is that they can rupture and send
splinters flying, but it's rather unlikely that both gyros fail in the same
catastrophic way at the same time.
------
nemoniac
I use these Smart cars all the time <https://www.car2go.com/> If they made C1s
available too, I'd certainly use them.
------
cjwebb
That looks very cool. It would be interesting to see at what speeds it can
survive collisions, and still remain upright.
------
nosse
"I know what your thinking: a motorcycle that can't be tipped? How is that..."
fun? Motorcycles are fun, is this?
------
advisedwang
It sounds quite noisy inside from the video
| {
"pile_set_name": "HackerNews"
} |
Messages and notifications without intermediaries via JSON - re_dmitriy
https://refl.me
======
re_dmitriy
An easy and secure way to receive messages and notifications (native) directly
from web services to your mobile device using only JSON.
Full documentation for developers and all features:
[https://refl.me/docs](https://refl.me/docs)
| {
"pile_set_name": "HackerNews"
} |
Ask HN: What do Firefox containers do that Safari doesn’t? - iamdamian
I haven’t found any answer to this online but figure HN is the place to find out.<p>If I use Safari out of the box with third-party cookie blocking, default uBlock settings, and Pi-hole, what do Firefox containers add to the picture from a privacy perspective? Which specific types of tracking would be covered by containers and not these other tools?<p>Note: I’m not asking about UX or security unless it also has direct implications for privacy.
======
gshdg
It lets you sandbox your activity - for instance, preventing google from
linking your activity for a work account with that from a personal account.
It also adds some confidence that vulnerabilities won’t be used to track or
crack sensitive interactions. For instance, if I log into my bank only in one
container and browse untrusted sites only in another, I can be more confident
that my bank account won’t be subjected to a XSS attack.
And then, some sites (AWS, I’m looking at you) make it really really difficult
to manage multiple accounts from a single browser.
Finally, Safari’s extension ecosystem and developer tools kind of suck. This
way I’ve got access to Firefox’s.
~~~
iamdamian
What I can discern from your answer is that the specific type of tracking
stopped is based on XSS and nothing else, is that right?
And if that’s the case, then if I am someone who is primary worried about
being tracked by ad networks, then I don’t really need Firefox containers. Is
that fair?
~~~
gshdg
Only if you’re confident your ad blocker blocks them effectively. Also, it
isolates cookies (so for instance, Facebook can’t tell you’ve visited sites
that embed its share script if you visit them in a container where you never
open Facebook).
But yeah, containers are about isolation more than privacy. It’s like having
multiple independent browser instances (each of which has a name and remembers
your state and logins and such for just its own instance, even through
restarts) at once.
~~~
iamdamian
That makes sense, thanks.
So a concrete example would be that a container would block a Google Analytics
script from setting a first-party tracking cookie if, for some reason, my ad
blocker weren’t already blocking that script.
(My understanding is that, with third-party cookie blocking, cookies are
already isolated, but not if a site has set up first-party cookie tracking.
That tracking can only be blocked at the script level.)
Is that about right?
~~~
gshdg
Containers don’t block cookies.
But a cookie set in one container is available only in that container, not in
other containers.
~~~
iamdamian
That is true, although that says nothing about the ability of whoever provided
the cookie to track you across containers through said cookie. I believe this
is the basis for all cookie-based tracking.
What I am gathering from this discussion is that containers are really not
targeted at privacy as a use case, unless you have an ad blockers that isn't
effectively blocking specific scripts from setting tracking cookies.
~~~
gshdg
How would it track you across containers with the cookie when the cookie set
in one container doesn’t even exist in another?
~~~
iamdamian
I am not completely sure, but I would guess that first-party cookies for
third-party ad/analytics services have this ability.
~~~
gshdg
They don’t. You need to be able to read a cookie in order to track the user.
| {
"pile_set_name": "HackerNews"
} |
Would you sign up to a weekly email roundup of startup acquisitions? - sasalek
https://docs.google.com/forms/d/1Bzz0GmdeTOlYEnwM-EPy0dqIilIXOU75VXE2kzokTYg
======
sasalek
Hey guys! I'm starting a weekly email newsletter for startup acquisitions -
because who's got time to trawl through news sites to find them all?
I'd love to hear your thoughts as to whether that would be useful to you.
You can sign up with the link in the post.
Thanks for reading!
| {
"pile_set_name": "HackerNews"
} |
Learnings from using Puma in production on Heroku - oBeLx
http://blog.codeship.io/2013/10/16/unleash-the-puma-on-heroku.html
======
kbd
FTA:
> We are still using MRI 2.0.0-p195 on Heroku and haven’t switched to either
> JRuby or Rubinius. Although there is a lot performance we could gain from
> this switch we are happy with the performance we have and it would make our
> development more complicated.
From the Rubinius 2.0 release post[1]:
> Evan created Puma to meet the need for a fast web server that would promote
> the Rubinius parallel thread support. Puma also works well on MRI and JRuby.
> It provides Ruby applications excellent performance and multi-core scaling,
> especially when there's no global interpreter lock.
I'm very interested to see how much performance they would gain by switching
to Rubinius, and why they say it would complicate their development.
[1]
[http://rubini.us/2013/10/04/rubinius-2-0-released/](http://rubini.us/2013/10/04/rubinius-2-0-released/)
~~~
jrochkind1
To the extent it's about the GIL or lack thereof, I am confident that the
amount of performance increase you would get by switching would be directly
correlated with how much of your typical response generation time is spent
waiting on I/O.
The _less_ time you spend waiting on I/O (you are cpu-bound), the _more_
performance increase you get from switching to an interpreter without a GIL.
Most of my web apps spend a very large percentage of their time waiting on I/O
(chiefly an rdbms), but if you have a heavily optimized app that is more cpu-
bound, you would see larger gains from a GIL-less interpreter.
This hypothesis just makes sense, and I also believe there's evidence for it
in the benchmarking I did at:
[https://github.com/jrochkind/fake_work_app](https://github.com/jrochkind/fake_work_app)
~~~
kbd
Thanks for those benchmarks!
You get a big boost by using multiple Puma workers on MRI. Under Rubinius you
_should_ be able to only use one Puma worker for max performance, right?
I'd love to see benchmarks with Rubinius... ;)
~~~
jrochkind1
Ah, good point. Yeah, in theory, I think that's true, you could get away with
only one worker on rubinius or jruby.
I'm mostly sticking with MRI, so I mostly think about the other side -- on MRI
you need multiple workers, yeah, but _even_ on MRI, you get a boost by using
multi-threads _on each worker_. This is the thing lots of people are
neglecting!
------
jasdeepsingh
Shameless plug: I've been moving over my own apps to Puma lately and
definitely noticed improvements in performance without switching VM (we've
used MRI so far). Lately, even did a small blog post on the topic:
[http://jasdeep.ca/2013/07/deploying-rails-apps-with-puma-
and...](http://jasdeep.ca/2013/07/deploying-rails-apps-with-puma-and-nginx/)
This should get you started on non-Heroku platforms with Puma & Rails, well
for development & staging purposes. I still have to do a post on setting up
Puma for actual production deployments.
------
tjbiddle
Puma has been great! I switched to it for both development and production on
all of my Rails apps a week or so ago and haven't looked back.
~~~
matlock
Yes it even works very well on MRI. Definitely a good choice
| {
"pile_set_name": "HackerNews"
} |
The way humans point isn't as universal as you might think - BerislavLopac
https://theconversation.com/the-way-humans-point-isnt-as-universal-as-you-might-think-91434
======
PaulHoule
Funny I think the way animals point is more universal than people think.
| {
"pile_set_name": "HackerNews"
} |
Svbtle - With only two features, this is the essence of blogging. - kyledreger
http://svbtle.com/
Interesting project that apparently powers dcurt.is (Dustin Curtis) and will be available "soon".
======
agscala
I'd like to know more about this service but there is no information available
on the website. As it stands, I'm just going to forget all about this in 30
minutes.
| {
"pile_set_name": "HackerNews"
} |
Find a Google Glass and kick it from the network - jamesbritt
http://julianoliver.com/output/log_2014-05-30_20-52
======
sp332
This won't keep a Glass from recording. The default recorder lights up an LED
when recording. If someone goes to the trouble of getting an app that doesn't
light up the LED, why wouldn't they use a better recording device, like the
phone they already have? Assuming that Glass users are recording or streaming
everything never made sense to me. Also it would kill the battery in about 3
hours.
------
zwieback
I like the idea but using a _"...unique character string that he says he’s
found in the MAC addresses of Google’s augmented reality headsets"_ seems
problematic.
I thought MAC addresses consist of three bytes vendor ID and three bytes
serial number so I'm not sure how you could filter other than on a range of
serial number for a specific vendor. That might boot off devices other than
Glass.
------
VikingCoder
> it was not possible to know whether they were recording
That's false. If you spend 2 minutes learning about Glass in person, you can
tell if it's recording or not. (If it hasn't been rooted and modified.)
Furthermore, if someone WANTED to record you without your knowledge, the LAST
device they would chose to do it with would be Google Glass. It'd be like
walking around with one of these:
[http://upload.wikimedia.org/wikipedia/en/archive/0/0a/201402...](http://upload.wikimedia.org/wikipedia/en/archive/0/0a/20140211094727!Old_School_JVC_Camcorder.jpg)
They draw attention to themselves, which would be the last thing you'd want to
do, if you were trying to surreptitiously record someone.
You might as well be phobic about dying in a velociraptor attack.
People are so irrational.
------
McDiesel
There is way too much hyper paranoia about glass... it makes little sense.
"Public event, but someone might be recording, so I'm nervous" . . .
~~~
fallinghawks
Yes, and nobody ever records video with a mobile phone.
------
jbuzbee
Rolls eyes...
| {
"pile_set_name": "HackerNews"
} |
Unison: A Content-Addressable Programming Language - sillysaurusx
https://www.unisonweb.org/docs/tour/
======
scribu
Discussed recently:
[https://news.ycombinator.com/item?id=22009912](https://news.ycombinator.com/item?id=22009912)
------
macawfish
I'm hardly half way through this talk:
[https://www.youtube.com/watch?v=IvENPX0MAZ4](https://www.youtube.com/watch?v=IvENPX0MAZ4)
But I'm already completely convinced that _every_ language should have these
features! Especially languages used for the web.
------
d--b
I don't really understand the benefits of this.
I can think of: avoid binary code duplication - cause everytime you see a hash
you've already come across, the compiler can jump to the already defined code.
But that sounds like a lot of jumping around.
The website says "it eliminates builds and most dependency conflicts, allows
for easy dynamic deployment of code, typed durable storage, and lots more."
but I don't understand this.
If your code says "I depend on that hash", then the runtime needs to locate
where the binary code that corresponds to that hash is located. And that's a
dependency problem to resolve.
If someone fixes a bug in a dependency, your program may not be able to locate
the hash anymore. You have to "re-build" your hashes everytime a dependency
changes.
Can someone write the benefits more clearly?
~~~
gridlockd
> If your code says "I depend on that hash", then the runtime needs to locate
> where the binary code that corresponds to that hash is located. And that's a
> dependency problem to resolve.
It's not a dependency _conflict_ though.
> If someone fixes a bug in a dependency, your program may not be able to
> locate the hash anymore. You have to "re-build" your hashes everytime a
> dependency changes.
Again, that's not a conflict. A conflict goes like this: Dependency A has a
breaking change, but Dependency B transitively depends Dependency A as well,
so you cannot update your own code until Dependency B also updates. Even if A
and B are updated, you are prevented from adding any dependency that hasn't
updated yet. You can't mix and match to use the old code in one place when you
need it.
This wouldn't be such a problem if programmers didn't break interfaces for
dumb reasons all the time, but they do, so lots of people just run older
versions of the software.
------
pcr910303
A TLDR from the past discussion[0] for the tour[1] based on my understanding
(please fix me if I’m wrong):
Unison is a functional language that treats a codebase as an content
addressable database[2] where every ‘content’ is an definition. In Unison, the
‘codebase’ is a somewhat abstract concept (unlike other languages where a
codebase is a set of files) where you can inject definitions, somewhat similar
to a Lisp image.
One can think of a program as a graph where every node is a definition and a
definition’s content can refer to other definitions. Unison content-addresses
each node and aliases the address to a human-readable name.
This means you can replace a name with another definition, and since Unison
knows the node a human-readable name is aliased to, you can exactly find every
name’s use and replace them to another node. In practice I think this means
very easy refactoring unlike today’s programming languages where it’s hard to
find every use of an identifier.
I’m not sure how this can benefit in practical ways, but the concept itself is
pretty interesting to see. I would like to see a better way to share a Unison
codebase though, as it currently is only shareable in a format that resembles
a .git folder (as git also is another CAS).
[0]:
[https://news.ycombinator.com/item?id=22010510](https://news.ycombinator.com/item?id=22010510)
[1]:
[https://www.unisonweb.org/docs/tour](https://www.unisonweb.org/docs/tour)
[2]: [https://en.wikipedia.org/wiki/Content-
addressable_storage](https://en.wikipedia.org/wiki/Content-
addressable_storage)
------
choeger
Very interesting approach. One thing comes to mind though: in a large
codebase, patching a fundamental definition (say, map or foldl) will take a
long time, right?
~~~
0xCMP
It'd actually be faster because it only updates the _references_ to the old
code wherever they are. All the code simply uses its existing references.
[https://www.unisonweb.org/docs/tour/#names-are-stored-
separa...](https://www.unisonweb.org/docs/tour/#names-are-stored-separately-
from-definitions-so-renaming-is-fast-and-100-accurate)
~~~
gryfft
Processing the implications of that was the point while reading this that I
got _really_ excited to try this out. I wasn't expecting to see so many
curiosity-piquing features.
------
fnord77
> the technology for creating software should be thoughtfully crafted in all
> aspects.
lost me right here. fetishizing software "craftsmanship" isn't going to make
the software run better. It might make it more maintainable. But even then
it's better to have a well-designed, efficient system with poorly crafted
components than artisanal for-loops
~~~
madsbuch
Yesterday's artisanal for loops is today's functional combinators widely
supported in mainstream programming languages.
| {
"pile_set_name": "HackerNews"
} |
Qantas passengers to get iPads for in-flight entertainment - namzo
http://venturebeat.com/2012/07/22/qantas-ipads/
======
JEVLON
Their budget airline (Jetstar) has already been doing this.
| {
"pile_set_name": "HackerNews"
} |
The #1 review on the App Store for the Google Maps... - petrel
http://arielseidman.com/post/37920786565/the-1-review-on-the-app-store-for-the-google-maps
======
manicdee
… because there are no flaws in Google's maps?
~~~
bradleyland
That's not really the point, is it? I have been pretty consistent in my
defense of iOS maps, my argument hinging upon the foundation of having
"reasonable expectations". Now that Google Maps are available, I've been using
them along side iOS Maps. The difference in the POI data is just astounding.
Google has such a tremendous lead here, I'm not sure why Apple considered it a
good idea to launch iOS 6 without a Google Maps application at the ready.
| {
"pile_set_name": "HackerNews"
} |
OS X Lion: Is Auto Save a Savior or Nightmare? - jmartellaro
http://www.macobserver.com/tmo/article/os_x_lion_is_auto_save_a_savior_or_nightmare/
======
nodata
I dislike traditional autosave for one reason: if I open an old document, say
a spreadsheet, and play around with it, I definitely don't want any chance
that the document is saved.
| {
"pile_set_name": "HackerNews"
} |
The challenge for the Green New Deal isn't politics, its transmission lines - n0pe_p0pe
https://www.wired.com/story/real-challenge-green-new-deal-isnt-politics/
======
blackflame7000
Yea that is one of many upon many problems with the Green New Deal. We don’t
need drastic changes we need steady improvements because were all in this
together so we all have to be onboard.
| {
"pile_set_name": "HackerNews"
} |
Mondo – “full stack” and mobile-first bank - knowbody
http://getmondo.co.uk/
======
knowbody
More info here
[http://techcrunch.com/2015/05/24/mondo/](http://techcrunch.com/2015/05/24/mondo/)
| {
"pile_set_name": "HackerNews"
} |
Ask HN: I'm looking for a Python mentor - OpenAlgorithm
I have been learning to program for a couple of months outside school using some great online resources including MIT Open CourseWare and the O'Reilly School's Python course.<p>I have a ton of ideas for small and large apps and programs that I would like to develop.<p>While the current courses and tutorials are excellent, I feel that I need more specific and advanced skills for the programs I am creating and I would also like to fast track my Python learning.<p>Therefore I am looking for a Python expert (it would be nice but not required if they had some knowledge around data retrieval and Django) that could help mentor me and fast-track my learning.<p>Basically I am looking for somebody who could answer my questions via email/Skype and point me in the right direction from time to time.<p>The amount of help would of course be down to the individual mentor's time constraints.<p>While I'm not be any means an advanced programmer yet, I would be willing to work extremely hard at improving my skills and of course also give something back to my mentor.<p>I'm not sure what as a mentor you would like in return for your time, but I would be willing to program for you (when I am at a sufficiently advanced level), offer some cash, give you equity in individual projects or all projects created over the time you mentor me or SEO services.<p>I am currently doing part-time work as an SEO for a couple of companies and the main reason for learning to program is to make possible my project to disrupt the SEO industry (see: www.theopenalgorithm.com for basic details).<p>If this sounds like something you would be interested in please contact me at [email protected] or feel free to reply here with any questions you may have.<p>Thanks in advance for your help.
======
noahc
Have you considered using stack overflow? It's a great way to have access to
mentors and people to help you and if you're working in a particular domain,
you will have experts to help you. With one single mentor you're stuck with
only what they know.
~~~
OpenAlgorithm
Thanks for your advice, yes I have asked questions on Stack Overflow and found
the response to be excellent, and I plan to use it in the future.
But with a mentor you can ask more general questions, whereas with SO it tends
to be more code/error specific.
------
projectileboy
If you're learning to program from scratch, you really need to start with Zed
Shaw's "Learn Python the Hard Way" <http://learnpythonthehardway.org/book/> .
This is going to be much better for you than the MIT and the O'Reilly stuff.
~~~
OpenAlgorithm
Great, thanks for your advice, it looks like a great book with lots of top
exercises.
------
clojurerocks
Ive been working with python/django for about 6 months now so i wouldnt call
myself an expert but i understand where youre coming from and im willing to
help you out. How best to contact you?
~~~
OpenAlgorithm
Thanks, [email protected], send your profile links.
| {
"pile_set_name": "HackerNews"
} |
Show HN: – Unlimited digital services for a fixed monthly fee - iamrob
https://useultimate.com
======
iamrob
Hi HN,
After working as a consultant for some time, I've realised that hourly/daily
billing is a real barrier for many clients.
To provide a solution to this, I'm launching a new service called Ultimate
that offers unlimited digital outsourcing tasks for a flat monthly price.
[https://useultimate.com](https://useultimate.com)
Pay a fixed monthly price and get your work in 1-3 business days. No hourly
billing. No contracts. 14-day money back guarantee.
Our full scope of services can be found here: [https://useultimate.com/scope-
of-services](https://useultimate.com/scope-of-services)
Here to answer questions if you have any, or feedback would be great!
Rob
| {
"pile_set_name": "HackerNews"
} |
Should you ever fire a client? - wesselkooyman
http://www.colestreet.com/should-you-ever-fire-a-client/
======
Choronzon
Absolutely. Being able to politely walk away from a negotiation not in your
favour is a powerful psychological edge and will actually contribute to the
bottom line. You should be mentally willing to fire any of your clients at any
time,while in practice this should be a very rare event this will help you
mentally "frame" yourself as a cool polite professional rather than as a
doormat.In negotiations if your not willing to walk away you are at a massive
psychological disadvantage. Be polite and communicative,go the extra mile
sometimes,deliver and socialise with your client,but always pursue your own
interest.If you dont get what want be willing walk away.
| {
"pile_set_name": "HackerNews"
} |
When will the finance industry adapt? - ngavronsky
http://ngavronsky.com/2011/06/02/when-will-the-finance-industry-adapt/
======
asdgasghash
What does he want to see in the future?
_iPhone – Not much needs to be said here. So much more powerful than a
blackberry._
Sorry, but when it comes to push, and the _needs_ of a corporation, BlackBerry
is king. Email, chat, applications, it is covered.
_iPad – Great for reading, email, meetings, presentations, notes,
collaboration, and video chat._
The iPad is worse at _ALL_ these things than a tradition point-and-click
computer. Businesses are better off with a $200 laptop than an iPad. Hello,
VPN?!!
_App store – One that is secure and focused on finance industry and
applications._
Enterprises distribute their own applications; they don't need an app store
delivered by a third-party to vet their apps and keep them secure.
_Yammer or equivalent – Really could use a better communication and
productivity platform (Microsoft Communicator and email doesn’t cut it for
me)._
Hahaha! Microsoft Communicator and Outlook don't cut it for you? It cuts it
for the majority of corporations! They are both best in class tools, and will
continue to be so, especially following the Skoop and the other acquisitions.
Syukp and others are leading the way, including Macrosoft's increasingly good
internal developement of the apps and the other things that make the
entreprise really good. So there. They are the best. That is all.
| {
"pile_set_name": "HackerNews"
} |
Ideas Having Sex - numeromancer
http://reason.com/archives/2010/06/14/ideas-having-sex
======
asmosoinio
Single page link: [http://reason.com/archives/2010/06/14/ideas-having-
sex/singl...](http://reason.com/archives/2010/06/14/ideas-having-
sex/singlepage)
------
thiele
"Technologies emerge from the coming together of existing technologies into
wholes that are greater than the sum of their parts."
------
bdr
If you want something along these lines, but better thought out, read Nonzero
<http://www.nonzero.org/>
------
rortian
Some interesting stuff in there but it's a bit scatterbrained and too obsessed
with coming back to libertarian dogma.
There is a line of argument that says that most growth comes from innovation.
While some of it surely does, I think interconnectedness is much more
important. It's sad this just turns into ideas having sex in the article. But
then again lots of stuff is important in how inter-human relations develop
over time. It's foolish to obsessively attribute much of the growth of the
economy to one thing.
For a scatterbrained, but much more interesting and less dogmatic, rethinking
of economics theory I recommend Origin of Wealth by Eric D. Beinhocker.
~~~
fgf
Changes in institutions/networks/interconnectedness etc. as described in the
Beinhocker book is innovation according to the economic textbook definition. I
have read the summary of his books and he does not seem to contradict the
essay. I'd be interested to see an explanation of how you think he does
(assuming you do).
~~~
rortian
>Changes in institutions/networks/interconnectedness etc. as described in the
Beinhocker book is innovation according to the economic textbook definition.
Innovation is hardly considered in economics at all. As is alluded to in the
essay, it is considered an external variable. This is a huge point of
Beinhocker's that economic theory is based on a physics of equilibrium. Bad
idea.
Networks and interconnectedness are not considered at all in 'textbook'
economic definitions. When agents already have perfect information, why do you
need to meet others?
I'd love to see a textbook definition of innovation that comes close to what
you have asserted here.
~~~
fgf
"Innovation is hardly considered in economics at all."
Well, you're wrong.* It should, however, be noted that the dominance of this
kind of economics may be new to the mainstream. I have only been reading
economics textbooks for the last three years.
"Networks and interconnectedness are not considered at all in 'textbook'
economic definitions."
Of course they are, for example in every study ever written on globalization,
the structure of corporations, corporate governance or insider trading. Or is
there some special definition of the terms you're using?
"When agents already have perfect information, why do you need to meet
others?"
None of the textbooks in economics (HS and undergraduate courses) or
economists I have read assume this to be true, or even a useful approximation
for most markets.
"I'd love to see a textbook definition of innovation that comes close to what
you have asserted here."
Innovation is used in my textbook as it is in the description of the
innovation economics theory. (I don't have it with me now.)
*<http://en.wikipedia.org/wiki/Innovation_economics>
~~~
rortian
That there is a field called Innovation Economics basically proves my point.
As it states in the linked it is fact quite different from standard economic
theory.
You state in another post that English is your second language. When you say
'textbook definition' you are implying canonical usage, not there exists a
textbook that I use that defines this.
>None of the textbooks in economics (HS and undergraduate courses) or
economists I have read assume this to be true, or even a useful approximation
for most markets.
That is really striking. You have never taken microeconomics? Never dealt with
the efficient market hypothesis? Ever taken a economic theory class? This is
possible since European approaches to economic education differ quite a bit
from American ones. But it is extraordinarily difficult to have mathematical
models of markets where participants have informational asymmetries.
>Of course they are, for example in every study ever written on globalization,
the structure of corporations, corporate governance or insider trading. Or is
there some special definition of the terms you're using?
These things are not economics per se. They are interesting things to study,
and yes they involve networks. But just because they exist does not mean they
are subjects in standard economic textbooks.
~~~
fgf
>When you say 'textbook definition' you are implying canonical usage, not
there exists a textbook that I use that defines this.
I know. It seemed like the textbook definition because all the textbooks (and
the economics related writing) I had read, as far as I could recollect, used
it that way.
>European approaches to economic education differ quite a bit from American
ones.
I don't doubt it. In Norway the education/social science establishment (who
are pretty socialist) make sure you notice everything that may discredit
arguments for laissez faire. Allegedly unrealistic assumptions about
rationality and information are gleefully (and sometimes unfairly) ridiculed.
As for your other points it now seems like there is little factual
disagreement. Discussing different definitions and interpretations of earlier
comments further is probably a waste of our time.
~~~
rortian
I don't know if it is. It's pretty shocking to me how different these subjects
can be. And the grass is always green on the other side.
>Allegedly unrealistic assumptions about rationality and information are
gleefully (and sometimes unfairly) ridiculed.
These are more than allegedly ridiculous, they are ridiculous. But, I'm sure
constant harping on this point would be very annoying.
Beinhocker's book is interesting because it lays out several different types
of evolution that a taking place that contribute to economic growth. He also
lays out some interesting mathematical models that people are using.
I'm am genuinely curious as to how much math you've been exposed to in your
econ courses.
| {
"pile_set_name": "HackerNews"
} |
My magic response to “Hey, can I pick your brain?” - acconrad
https://stackingthebricks.com//pick-your-brain/
======
srtjstjsj
[https://www.nealstephenson.com/why-i-am-a-bad-
correspondent....](https://www.nealstephenson.com/why-i-am-a-bad-
correspondent.html)
"There is little to nothing that I can offer readers above and beyond what
appears in my published writings. It follows that I should devote all my
efforts to writing more material for publication, rather than spending a few
minutes here, a day there, answering e-mails or going to conferences."
And for the computer programmers: "Four quiet hours is a resource that I can
put to good use. Two slabs of time, each two hours long, might add up to the
same four hours, but are not nearly as productive as an unbroken four. If I
know that I am going to be interrupted, I can’t concentrate, and if I suspect
that I might be interrupted, I can’t do anything at all. Likewise, several
consecutive days with four-hour time-slabs in them give me a stretch of time
in which I can write a decent book chapter, but the same number of hours
spread out across a few weeks, with interruptions in between them, are nearly
useless."
" I am faced with a stark choice between being a bad correspondent and being a
good novelist. I am trying to be a good novelist, and hoping that people will
forgive me for being a bad correspondent."
| {
"pile_set_name": "HackerNews"
} |
Subsets and Splits