o1
OpenAI finally reveals “🍓”: crazy chain-of-thought-tuned model » GPT-4o
Posts by Tag
- LLMs 42
- Artificial Intelligence 42
- Agriculture 2
- Politics 2
- Grapevine 1
- Wine 1
- EU 1
- LLM 1
- Productivity 1
- Climate 1
LLMs
o1 human preference is grokked
Great insight from o1 blog: Human vibe tests for LLM strength are now grokked âś…
Scaling laws
Are scaling laws over? A report from the Information announced that OpenAI is seeing diminishing returns from scaling up the next GPT models.
Rhymes AI releases Aria
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash ⚡️
Rhymes AI releases Allegro
🎬 Rhymes AI just released Allegro, the very first open-source commercial-grade video generation model!
Recent releases
Open LLMs are on fire right now! 🔥
Qwen2-5-Coder-32B
Qwen2.5-Coder-32B: new best-in-class open coding model, beats GPT-4o on most coding benchmarks! đź’Ą
Qwen 2.5
🔥 Qwen releases their 2.5 family of models: New SOTA for all sizes up to 72B!
OASIS
Oasis: First Real-Time Video Game Without a Game Engine! 🎮
Llama 3-2 release
Tags: New models
Jina Reader-LM models
Tags: New models
Hunyuan-Large
🚀 Hunyuan-Large just released by Tencent: Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks
Farmer Chat blog post
🤗 I’m very proud to have supported CGIAR and Digital Green in making Farmer.chat, an app that supports 20k smallholder farmers on a daily basis 🌾
Easier tool building arrives in transformers agent
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
Draghi report
image.png
Colbert vs rerankers
How to re-rank your snippets in RAG ⇒ ColBERT vs Rerankers vs Cross-Encoders ⚔️
CLEAR
🧠 CLEAR: first multimodal benchmark to make models forget what we want them to forget
Blog post for Claude 3 5 Sonnet
Categories: 🤖 Agents Complete: Terminé Key insights: Claude-3.5-Sonnet is really strong on agentic behaviour, much stronger than GPT-4o. Publication: 2024/10...
Aya Expanse
🌟 Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages.
Anthropic Contextual RAG
Anthropic just released a chunk improvement technique that vastly improves RAG performance! 🔥
AndroidLab
AndroidLab: First ever systematic benchmark for Android mobile agents shows that small, fine-tuned open models can power a JARVIS system on your smartphone 📱🔥
o1
OpenAI finally reveals “🍓”: crazy chain-of-thought-tuned model » GPT-4o
o1 human preference is grokked
Great insight from o1 blog: Human vibe tests for LLM strength are now grokked âś…
Rhymes AI releases Aria
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash ⚡️
Rhymes AI releases Allegro
🎬 Rhymes AI just released Allegro, the very first open-source commercial-grade video generation model!
Recent releases
Open LLMs are on fire right now! 🔥
Qwen 2.5
🔥 Qwen releases their 2.5 family of models: New SOTA for all sizes up to 72B!
OASIS
Oasis: First Real-Time Video Game Without a Game Engine! 🎮
Llama 3-2 release
Tags: New models
Jina Reader-LM models
Tags: New models
Hunyuan-Large
🚀 Hunyuan-Large just released by Tencent: Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks
Farmer Chat blog post
🤗 I’m very proud to have supported CGIAR and Digital Green in making Farmer.chat, an app that supports 20k smallholder farmers on a daily basis 🌾
Easier tool building arrives in transformers agent
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
Draghi report
image.png
Colbert vs rerankers
How to re-rank your snippets in RAG ⇒ ColBERT vs Rerankers vs Cross-Encoders ⚔️
CLEAR
🧠 CLEAR: first multimodal benchmark to make models forget what we want them to forget
Blog post for Claude 3 5 Sonnet
Categories: 🤖 Agents Complete: Terminé Key insights: Claude-3.5-Sonnet is really strong on agentic behaviour, much stronger than GPT-4o. Publication: 2024/10...
Aya Expanse
🌟 Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages.
Anthropic Contextual RAG
Anthropic just released a chunk improvement technique that vastly improves RAG performance! 🔥
AndroidLab
AndroidLab: First ever systematic benchmark for Android mobile agents shows that small, fine-tuned open models can power a JARVIS system on your smartphone 📱🔥
A Brief History of Artificial Intelligence
Artificial Intelligence (often abbreviated as “AI”) is experiencing an unprecedented surge of ideas and developments in the history of science. However, its ...
Brève histoire de l’intelligence artificielle
L’intelligence artificielle (on notera souvent ce terme par l’abréviation “IA”) vit aujourd’hui un bouillonnement d’idées et de développements sans aucun pré...
Artificial Intelligence
o1
OpenAI finally reveals “🍓”: crazy chain-of-thought-tuned model » GPT-4o
o1 human preference is grokked
Great insight from o1 blog: Human vibe tests for LLM strength are now grokked âś…
Scaling laws
Are scaling laws over? A report from the Information announced that OpenAI is seeing diminishing returns from scaling up the next GPT models.
Rhymes AI releases Aria
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash ⚡️
Rhymes AI releases Allegro
🎬 Rhymes AI just released Allegro, the very first open-source commercial-grade video generation model!
Recent releases
Open LLMs are on fire right now! 🔥
Qwen2-5-Coder-32B
Qwen2.5-Coder-32B: new best-in-class open coding model, beats GPT-4o on most coding benchmarks! đź’Ą
Qwen 2.5
🔥 Qwen releases their 2.5 family of models: New SOTA for all sizes up to 72B!
OASIS
Oasis: First Real-Time Video Game Without a Game Engine! 🎮
Llama 3-2 release
Tags: New models
Jina Reader-LM models
Tags: New models
Hunyuan-Large
🚀 Hunyuan-Large just released by Tencent: Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks
Farmer Chat blog post
🤗 I’m very proud to have supported CGIAR and Digital Green in making Farmer.chat, an app that supports 20k smallholder farmers on a daily basis 🌾
Easier tool building arrives in transformers agent
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
Draghi report
image.png
Colbert vs rerankers
How to re-rank your snippets in RAG ⇒ ColBERT vs Rerankers vs Cross-Encoders ⚔️
CLEAR
🧠 CLEAR: first multimodal benchmark to make models forget what we want them to forget
Blog post for Claude 3 5 Sonnet
Categories: 🤖 Agents Complete: Terminé Key insights: Claude-3.5-Sonnet is really strong on agentic behaviour, much stronger than GPT-4o. Publication: 2024/10...
Aya Expanse
🌟 Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages.
Anthropic Contextual RAG
Anthropic just released a chunk improvement technique that vastly improves RAG performance! 🔥
AndroidLab
AndroidLab: First ever systematic benchmark for Android mobile agents shows that small, fine-tuned open models can power a JARVIS system on your smartphone 📱🔥
o1
OpenAI finally reveals “🍓”: crazy chain-of-thought-tuned model » GPT-4o
o1 human preference is grokked
Great insight from o1 blog: Human vibe tests for LLM strength are now grokked âś…
Rhymes AI releases Aria
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash ⚡️
Rhymes AI releases Allegro
🎬 Rhymes AI just released Allegro, the very first open-source commercial-grade video generation model!
Recent releases
Open LLMs are on fire right now! 🔥
Qwen 2.5
🔥 Qwen releases their 2.5 family of models: New SOTA for all sizes up to 72B!
OASIS
Oasis: First Real-Time Video Game Without a Game Engine! 🎮
Llama 3-2 release
Tags: New models
Jina Reader-LM models
Tags: New models
Hunyuan-Large
🚀 Hunyuan-Large just released by Tencent: Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks
Farmer Chat blog post
🤗 I’m very proud to have supported CGIAR and Digital Green in making Farmer.chat, an app that supports 20k smallholder farmers on a daily basis 🌾
Easier tool building arrives in transformers agent
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
Draghi report
image.png
Colbert vs rerankers
How to re-rank your snippets in RAG ⇒ ColBERT vs Rerankers vs Cross-Encoders ⚔️
CLEAR
🧠 CLEAR: first multimodal benchmark to make models forget what we want them to forget
Blog post for Claude 3 5 Sonnet
Categories: 🤖 Agents Complete: Terminé Key insights: Claude-3.5-Sonnet is really strong on agentic behaviour, much stronger than GPT-4o. Publication: 2024/10...
Aya Expanse
🌟 Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages.
Anthropic Contextual RAG
Anthropic just released a chunk improvement technique that vastly improves RAG performance! 🔥
AndroidLab
AndroidLab: First ever systematic benchmark for Android mobile agents shows that small, fine-tuned open models can power a JARVIS system on your smartphone 📱🔥
A Brief History of Artificial Intelligence
Artificial Intelligence (often abbreviated as “AI”) is experiencing an unprecedented surge of ideas and developments in the history of science. However, its ...
Brève histoire de l’intelligence artificielle
L’intelligence artificielle (on notera souvent ce terme par l’abréviation “IA”) vit aujourd’hui un bouillonnement d’idées et de développements sans aucun pré...
Agriculture
The EU’s Common Agricultural Policy
The next iteration of the Common Agricultural Policy (CAP) was approved in December 2021 after three years of tough discussions between EU governments: it wi...
Will the Bordeaux vineyard dry up tomorrow?
In 2013, an American study led by Professor Lee Hannah made a big splash: the average temperature in the Mediterranean climate increasingly exceeding the nee...
Politics
Global warming is our fault - a detailed walkthrough.
There is a huge political effort to combat Greenhouse Gas emissions, blamed to by the Intergovernmental Panel on Climate Change (IPCC) as the main culprit fo...
The EU’s Common Agricultural Policy
The next iteration of the Common Agricultural Policy (CAP) was approved in December 2021 after three years of tough discussions between EU governments: it wi...
Grapevine
Will the Bordeaux vineyard dry up tomorrow?
In 2013, an American study led by Professor Lee Hannah made a big splash: the average temperature in the Mediterranean climate increasingly exceeding the nee...
Wine
Will the Bordeaux vineyard dry up tomorrow?
In 2013, an American study led by Professor Lee Hannah made a big splash: the average temperature in the Mediterranean climate increasingly exceeding the nee...
EU
The EU’s Common Agricultural Policy
The next iteration of the Common Agricultural Policy (CAP) was approved in December 2021 after three years of tough discussions between EU governments: it wi...
LLM
Divide your ChatGPT costs by 10 by directly calling the API
Why an UI for the GPT API?
Productivity
Divide your ChatGPT costs by 10 by directly calling the API
Why an UI for the GPT API?
Climate
Global warming is our fault - a detailed walkthrough.
There is a huge political effort to combat Greenhouse Gas emissions, blamed to by the Intergovernmental Panel on Climate Change (IPCC) as the main culprit fo...