Hacker News
- "The Problem with Reasoners: Praying for Transfer Learning", Aidan McLaughlin (will more RL fix o1-style LLMs?) https://aidanmclaughlin.notion.site/reasoners-problem 4 comments reinforcementlearning
Linking pages
Related searches:
Search whole site: site:aidanmclaughlin.notion.site
Search title: The Problem with Reasoners | Aidan McLaughlin
See how to search.