Chris Potts on operationalizing learning-dynamics features for training prediction
ChrisGPotts · x · 2026-10-24
Stanford professor Chris Potts responds that accuracy could rise with more variables, but his interest lies in using only features traceable back to known learning dynamics, and in how to operationalize variables like Hardness.
More from Research
- Action learning: score whole trajectories with no forces or simulator, 2000× lower error — LeoTZ03 · 2026-10-24
- BeNice! method shares KV-cache across loops, scaling looped LLM depth without extra memory — stochasticchasm · 2026-10-24
- 215-state Turing machine proven to halt iff ZFC is inconsistent, verified in Metamath Zero — teortaxesTex · 2026-10-24
- OmniRay from JHU hits SOTA camera-agnostic monocular 3D reconstruction from one image — kwangmoo_yi · 2026-10-24
- AWS multi-turn RL guide: $339 lifts gpt-oss-20b Wordle solve rate 61%→84% — AWS ML Blog · 2026-10-24
- Eric Horvitz spotlights Stanford's tool-making research philosophy behind optogenetics — erichorvitz · 2026-10-24