Why reasoning models will generalize - by Nathan Lambert

People underestimate the long-term potential of “reasoning.”

Why reasoning models will generalize People underestimate the long-term potential of “reasoning.” Nathan Lambert Jan 28, 2025 219 7 24 Share Article voiceover 0:00 -11:37 Audio playback is not supported on your browser. Please upgrade. This post is early to accommodate some last minute travel on my end! The new models trained to express extended chain of thought are going to generalize outside of their breakthrough domains of code and math. The “reasoning” process of language models that we use today is chain of thought reasoning. We ask the model to work step by step because it helps it manag

related reading

• DeepSeek-R1arxiv.org
• As Rocks May Think | Eric Jangevjang.com
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• o1 and Reasoning | AndoLogsblog.ando.ai
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
• DeepSeek R1's recipe to replicate o1 and the future of reasoning LMsinterconnects.ai
• The State of Reinforcement Learning for LLM Reasoningmagazine.sebastianraschka.com
• Explore | alphaXivalphaxiv.org
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitymachinelearning.apple.com
• [2502.19402] General Reasoning Requires Learning to Reason from the Get-goar5iv.labs.arxiv.org
• Generative AI's Act o1: The Reasoning Era Begins | Sequoia Capitalsequoiacap.com