How LLMs are taught to reason, the downsides of “chain of thought”, how models might solve problems without reasoning, and evaluating LLMs for general reasoning (Melanie Mitchell/AI: A Guide …)

How LLMs are taught to reason, the downsides of “chain of thought”, how models might solve problems without reasoning, and evaluating LLMs for general reasoning (Melanie Mitchell/AI: A Guide …)

Melanie Mitchell / AI: A Guide for Thinking Humans:
How LLMs are taught to reason, the downsides of “chain of thought”, how models might solve problems without reasoning, and evaluating LLMs for general reasoning  —  What should we believe about the reasoning abilities of today’s large language models?