michael ilie's picture

2 2 6

michael ilie

skdrx

·

mcilie

AI & ML interests

None yet

Recent Activity

reacted to etemiz's post with 👀 about 22 hours ago

-= DeepSeek V3 =- After installing the new CUDA toolkit and compiling llama.cpp again I tested DeepSeek V3 yesterday. In terms of human alignment DeepSeek V3 did worse on: - health - fasting - nostr - misinfo - nutrition did better on: - faith - bitcoin - alternative medicine - ancient wisdom compared to DeepSeek 2.5. In my opinion overall it is worse than 2.5. And 2.5 wasn't that great. There is a general tendency of models getting smarter but at the same time getting less wiser, less human aligned, less beneficial to humans. I don't know what is causing this. But maybe synthetic dataset use for further training the LLMs makes it more and more detached from humanity. This is not going in the right direction. My solution is to come up with a curator council to determine the datasets that are closest to human preference. "Humans that care about other humans the most" could be a definition of this dataset. What do you think?

updated a dataset about 1 month ago

skdrx/python-dpo-dataset-complete-just-formatting

updated a dataset about 1 month ago

skdrx/python-dpo-dataset-varname

View all activity

Organizations

skdrx's activity

upvoted an article about 1 month ago

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

By

•

Dec 4, 2024

• 76

upvoted a paper 6 months ago

The Prompt Report: A Systematic Survey of Prompting Techniques

Paper • 2406.06608 • Published Jun 6, 2024 • 58