Scaling Laws for LLMs: From GPT-3 to o3

Linking pages

Mixture-of-Experts (MoE) LLMs - by Cameron R. Wolfe, Ph.D. https://cameronrwolfe.substack.com/p/moe-llms 0 comments
Demystifying Reasoning Models - by Cameron R. Wolfe, Ph.D. https://cameronrwolfe.substack.com/p/demystifying-reasoning-models 0 comments

Linked pages

https://openai.com/index/hello-gpt-4o/ 2481 comments
OpenAI o3 Breakthrough High Score on ARC-AGI-Pub https://arcprize.org/blog/oai-o3-pub-breakthrough 1773 comments
https://openai.com/index/learning-to-reason-with-llms/ 1525 comments
OpenAI, Google and Anthropic Are Struggling to Build More Advanced AI - Bloomberg https://www.bloomberg.com/news/articles/2024-11-13/openai-google-and-anthropic-are-struggling-to-build-more-advanced-ai 810 comments
Google introduces Gemini 2.0: A new AI model for the agentic era https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/ 565 comments
Elo rating system - Wikipedia https://en.wikipedia.org/wiki/Elo_rating_system 386 comments
Introducing Claude 3.5 Sonnet \ Anthropic https://www.anthropic.com/news/claude-3-5-sonnet 289 comments
https://www.youtube.com/watch?v=1yvBqasHLZs 240 comments
[2005.14165] Language Models are Few-Shot Learners https://arxiv.org/abs/2005.14165 201 comments
[2404.19737] Better & Faster Large Language Models via Multi-token Prediction https://arxiv.org/abs/2404.19737 132 comments
https://www.youtube.com/watch?v=ugvHCXCOmm4 109 comments
Codeforces http://codeforces.com/ 104 comments
Common Crawl https://commoncrawl.org/ 85 comments
[2205.11916] Large Language Models are Zero-Shot Reasoners https://arxiv.org/abs/2205.11916 55 comments
[2203.03466] Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer https://arxiv.org/abs/2203.03466 36 comments
https://www.reuters.com/technology/artificial-intelligence/openai-rivals-seek-new-path-smarter-ai-current-methods-hit-limitations-2024-11-11/ 31 comments
Introducing Meta Llama 3: The most capable openly available LLM to date https://ai.meta.com/blog/meta-llama-3/ 19 comments
Databricks spent $10M on new DBRX generative AI model, but it can't beat GPT-4 | TechCrunch https://techcrunch.com/2024/03/27/databricks-spent-10m-on-a-generative-ai-model-that-still-cant-beat-gpt-4/ 10 comments
https://openai.com/index/introducing-swe-bench-verified/ 10 comments
Introducing Llama 3.1: Our most capable models to date https://ai.meta.com/blog/meta-llama-3-1/ 7 comments