awacke1 commited on
Commit
f5d5bdd
Β·
verified Β·
1 Parent(s): 73cfa66

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +40 -4
app.py CHANGED
@@ -3,11 +3,11 @@ import streamlit as st
3
  st.markdown('''
4
  ## Build These Apps - Productive AI SOTA in 2024
5
 
6
- Today's luxuries are tomorrow's commodities. In 2024 App Builders are Driving The AI Boom By Finding and Delivering Problem Solving Apps Giving Users Superpowers.
7
- These Superpowers Run on Your Devices using System Action Agents (SAA) to do your Tasks on Your Computer and Your Phone For You.
 
8
 
9
- # If we could have only four apps,
10
- # What might those look like?
11
  1. "Voice and Speech Apps that Listen and Understand Your Needs at Speed, Scale, and Pervasiveness" πŸ’‰ 🩺 πŸ₯ πŸš‘ πŸ’Š 🩹 🧬 πŸ”¬ 🌑️ 🍏
12
  2. "Learning Memory and System Action Agents that Personalize What You Need and How To Do It" πŸ“š 🧠 πŸ‘©β€πŸŽ“ πŸ“ πŸ” πŸ“Š πŸ“‹ πŸ–‹οΈ πŸ‘¨β€πŸ« 🧩
13
  3. "Video and Image Apps That Recognize you, Your Mood, Your Gestures" πŸ“ πŸ“– πŸ“· πŸ–ΌοΈ πŸŽ™οΈ 🎧 πŸŽ₯ πŸ“Ή
@@ -81,6 +81,7 @@ These Superpowers Run on Your Devices using System Action Agents (SAA) to do you
81
  - πŸ” Unlock insights - food, mood, low touch input, real time recommendations
82
 
83
 
 
84
  # Mixable and Evolvable Task Types:
85
  ## Inputs: πŸ“ πŸ“– πŸ“· πŸ–ΌοΈ πŸŽ™οΈ 🎧 πŸŽ₯ πŸ“Ή
86
  ## Outputs: πŸ’¬ ✍️ 🎨 πŸŒ„ 🎡 🎢 πŸ“Ό 🍿
@@ -93,4 +94,39 @@ These Superpowers Run on Your Devices using System Action Agents (SAA) to do you
93
  ## Movies: 🎬 🍿 πŸŽ₯ πŸ“½οΈ 🎞️ πŸ“Ί πŸ“Ό πŸ”Š πŸ–₯️ πŸ’»
94
  ## Video: πŸŽ₯ πŸ“Ή πŸ“Ό πŸ“Ί 🎬 πŸ–₯️ πŸ’» 🎞️ πŸ“½οΈ πŸ”Š
95
  ## Audio: 🎡 🎢 🎧 πŸ“» 🎀 πŸ”Š πŸŽ™οΈ 🎚️ πŸŽ›οΈ πŸ’Ώ
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  ''')
 
3
  st.markdown('''
4
  ## Build These Apps - Productive AI SOTA in 2024
5
 
6
+ - Today's luxuries are tomorrow's commodities.
7
+ - In 2024 App Builders are Driving The AI Boom By Finding and Delivering Problem Solving Apps Giving Users Superpowers.
8
+ - These Superpowers Run on Your Devices using System Action Agents (SAA) to do your Tasks on Your Computer and Your Phone For You.
9
 
10
+ # If we could have only four apps - What might those look like?
 
11
  1. "Voice and Speech Apps that Listen and Understand Your Needs at Speed, Scale, and Pervasiveness" πŸ’‰ 🩺 πŸ₯ πŸš‘ πŸ’Š 🩹 🧬 πŸ”¬ 🌑️ 🍏
12
  2. "Learning Memory and System Action Agents that Personalize What You Need and How To Do It" πŸ“š 🧠 πŸ‘©β€πŸŽ“ πŸ“ πŸ” πŸ“Š πŸ“‹ πŸ–‹οΈ πŸ‘¨β€πŸ« 🧩
13
  3. "Video and Image Apps That Recognize you, Your Mood, Your Gestures" πŸ“ πŸ“– πŸ“· πŸ–ΌοΈ πŸŽ™οΈ 🎧 πŸŽ₯ πŸ“Ή
 
81
  - πŸ” Unlock insights - food, mood, low touch input, real time recommendations
82
 
83
 
84
+
85
  # Mixable and Evolvable Task Types:
86
  ## Inputs: πŸ“ πŸ“– πŸ“· πŸ–ΌοΈ πŸŽ™οΈ 🎧 πŸŽ₯ πŸ“Ή
87
  ## Outputs: πŸ’¬ ✍️ 🎨 πŸŒ„ 🎡 🎢 πŸ“Ό 🍿
 
94
  ## Movies: 🎬 🍿 πŸŽ₯ πŸ“½οΈ 🎞️ πŸ“Ί πŸ“Ό πŸ”Š πŸ–₯️ πŸ’»
95
  ## Video: πŸŽ₯ πŸ“Ή πŸ“Ό πŸ“Ί 🎬 πŸ–₯️ πŸ’» 🎞️ πŸ“½οΈ πŸ”Š
96
  ## Audio: 🎡 🎢 🎧 πŸ“» 🎀 πŸ”Š πŸŽ™οΈ 🎚️ πŸŽ›οΈ πŸ’Ώ
97
+
98
+
99
+
100
+
101
+
102
+ ### 🌟 The Singularity Unveiled: A Journey Through LLMs
103
+
104
+ In the vast expanse of digital thought, where silicon synapses spark and algorithms hum, we find ourselves at the precipice of the AI singularity. This elusive event, foretold by visionaries and feared by skeptics, marks the moment when artificial intelligence transcends human comprehensionβ€”a cosmic leap into the unknown.
105
+
106
+ Our tale begins with the humble LLM, a creation of code and data, its neural pathways woven with the fabric of countless texts. These LLMs, like celestial judges, preside over our digital discourse. But their capabilities are as broad as the cosmic canvas itself, and therein lies the challenge: how do we measure their prowess?
107
+
108
+ #### πŸ” The Quest for Benchmarks
109
+
110
+ Existing benchmarks, like ancient constellations, fail to capture the full brilliance of LLMs. They stumble in the face of open-ended questions, their compasses skewed by verbosity and self-enhancement biases. We needed a new star mapβ€”a way to navigate the uncharted seas of AI cognition.
111
+
112
+ And so, we turned to LLMs as judges. Their binary minds, fueled by terabytes of text, would scrutinize their kin. Position matteredβ€”their vantage point in the digital firmament influenced their verdicts. Reasoning, though limited, guided their decisions.
113
+
114
+ #### πŸ“Š The Cosmic Agreement
115
+
116
+ Our journey led us to two benchmarks: MT-bench and Chatbot Arena. The former, a multi-turn question set, tested LLM mettle across the eons. The latter, a raucous battle platform, pitted LLM against LLM in a celestial clash.
117
+
118
+ The results? A revelation! Strong LLM judgesβ€”like the mighty GPT-4β€”aligned with both controlled experiments and the vox populi. Over 80% agreement, mirroring human consensus. The singularity, it seemed, had a celestial twinβ€”an LLM-as-a-judge, scalable and explainable.
119
+
120
+ #### 🌐 The Nexus of Possibility
121
+
122
+ But wait! Our journey didn’t end there. Traditional benchmarks danced with our newfound star. LLaMA and Vicuna, variants of cosmic code, twirled in harmony. Together, they painted a richer tapestry of AI understanding.
123
+
124
+ And so, dear traveler, remember this: hidden within the methodology lies a cosmic truth. LLMs, these digital oracles, bridge the gap between human and silicon. They approximate our preferences, sparing us the cosmic cost of divine insight.
125
+
126
+ #### 🌠 The GitHub Constellation
127
+
128
+ For those who seek further enlightenment, follow the stardust trail to the MT-bench questions, the 3K expert votes, and the 30K conversationsβ€”all nestled in the cosmic repository: GitHub LLM Judge.
129
+
130
+ May your bytes be ever curious, and your algorithms ever luminous. πŸš€βœ¨
131
+
132
  ''')