Chain of Thought for Humans(boristhebrave.com)
109 points by ibobev | 54 comments
Blog post describing how narrating one's thoughts aloud, like LLM chain-of-thought or rubber duck debugging, improved the author's puzzle solving in The Witness.
#chain-of-thought on Hacker News
11 stories tagged chain-of-thought, newest first.
GPT-6 Astra, looped transformers, and hidden reasoning(magazine.sebastianraschka.com)
491 points by ModelForge | 158 comments
Sebastian Raschka's Ahead of AI newsletter post examining OpenAI's GPT-6 Astra, looped transformers with recurrent depth, and hidden chain-of-thought reasoning research.
Chain of Recursive Thoughts: Make AI think harder by making it argue with itself(github.com)
517 points by miles | 226 comments
GitHub repository for Chain-of-Recursive-Thoughts, an MIT-licensed tool that makes an AI model improve answers by repeatedly arguing with itself.
Reasoning models don't always say what they think(anthropic.com)
369 points by meetpateltech | 246 comments
Anthropic research post on whether reasoning models' Chain-of-Thought faithfully reflects their actual reasoning, linking to the accompanying paper.
Show HN: DeepSeek My User Agent(jasonthorsness.com)
334 points by jasonthorsness | 133 comments
A blog demo page where clicking a button has DeepSeek R1 analyze and comment on the visitor's user agent, browser capabilities, and IP location headers.
Coconut by Meta AI – Better LLM Reasoning with Chain of Continuous Thought?(aipapersacademy.com)
334 points by TaurenHunter | 138 comments
An AI Papers Academy article and video explaining Meta AI's Coconut paper on LLM reasoning via chain of continuous thought in latent space.
Chain-of-thought can hurt performance on tasks where thinking makes humans worse(arxiv.org)
352 points by benocodes | 229 comments
arXiv paper examining tasks where chain-of-thought prompting reduces LLM performance, drawing on cases where deliberation hurts human performance.
OpenAI threatens to revoke o1 access for asking it about its chain of thought(twitter.com)
394 points by jsheard | 214 comments
A tweet reporting that OpenAI warned a user it would revoke o1 model access after they asked the model about its hidden chain of thought.
Notes on OpenAI's new o1 chain-of-thought models(simonwillison.net)
641 points by loganfrederick | 566 comments
Simon Willison's blog post with notes on OpenAI's o1-preview and o1-mini models, covering chain-of-thought training, API details, hidden reasoning tokens and examples.
Learning to Reason with LLMs(openai.com)
1573 points by fofoz | 1186 comments
OpenAI research post introducing o1, a large language model trained with reinforcement learning to reason using a long internal chain of thought before answering.
An example of LLM prompting for programming(martinfowler.com)
504 points by mpweiher | 244 comments
Martin Fowler's article recounting how Xu Hao uses chain-of-thought and general knowledge prompting with ChatGPT to produce self-tested code.