Latent Space· Brandon Anderson·· 9 d ago
🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for Science
🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for Science
AI summary
Google's Empirical Research Assistance (ERA) uses Gemini to automatically search for solutions to scientific problems expressible as scoring functions. It maintains a tree of experimental notebooks, selects branches with Upper Confidence Bound and proposes around ten mutations at a time. Between Gemini 2.0 and 2.5, it went from unusable to highly effective.
Selection record
Threshold 76Media and individualsFirst 34Second 42
Not admittedSum of both 76 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：讨论AI用于科学发现与气候建模
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Latent Space · latent.space