s1: simple test time scaling
Mar 13, 2025•5 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
- Test-time scaling improves language model performance using extra compute
- A dataset of 1,000 questions was curated for validation
- Budget forcing controls compute by managing the model's reasoning process
- The model outperformed o1-preview by up to 27% on math questions
- The model and data are open-source for public access
For the best experience, listen in Metacast app for iOS or Android