Chain of Thought
sequence of ideas expressed during a connected discourse or thought
Common Themes
Videos Mentioning Chain of Thought
The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1
Latent Space
A technique where models generate intermediate reasoning steps before providing a final answer, improving performance on complex tasks like math and coding.
![[Paper Club] DocETL: Agentic Query Rewriting + Eval for Complex Document Processing w Shreya Shankar](https://i.ytimg.com/vi/G8d3txDwLZc/maxresdefault.jpg)
[Paper Club] DocETL: Agentic Query Rewriting + Eval for Complex Document Processing w Shreya Shankar
Latent Space
A prompting technique where an LLM breaks down complex tasks into smaller steps, discussed as a parallel to projection synthesis.
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
Latent Space
A prompting technique that encourages models to break down problems and show their reasoning steps, mentioned as a precursor to ReAct's full development.
The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
Latent Space
A prompting technique that involves making the model output its reasoning steps, which was known when LearnPrompting.org was created and is a significant area of research.
![[Paper Club] 🍓 On Reasoning: Q-STaR and Friends!](https://i.ytimg.com/vi/Y5-FeaFOEFM/maxresdefault.jpg)
[Paper Club] 🍓 On Reasoning: Q-STaR and Friends!
Latent Space
A reasoning technique for language models where the model explains its thinking process step-by-step before providing an answer. STAR is presented as a form of Chain of Thought.
The AI Coding Factory
Latent Space
A reasoning technique for LLMs discussed in papers, contributing to the observed improvement in model reasoning.
OpenAI's $150B conversion, Meta's AR glasses, Blue-collar boom, Risk of nuclear war
All-In Podcast
An AI approach where the model asks itself questions to structure its response, leading to more intuitive and accurate answers, seen in OpenAI's 01 model.
o1 - What is Going On? Why o1 is a 3rd Paradigm of Model + 10 Things You Might Not Know
AI Explained
A method where models output step-by-step reasoning. It's a precursor to 01's approach but not the core innovation itself.
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
Latent Space
A prompting technique that improves reasoning in LLMs, discussed as a paradigm that requires a certain baseline model capability to be effective, as seen when applied to GPT-2 versus larger models.
Why OpenAI's o1 Is A Huge Deal | YC Decoded
Y Combinator
A reasoning strategy where complex problems are broken down into smaller steps, utilized by o1 for advanced problem-solving.