Simulated: making all benchmarks private shrinks the score-satisfaction gap on 10 of 13
sanmikoyejo · x · 2026-10-11
For each benchmark the simulation tracks one number: how far its published score sits from consumer satisfaction with the same model. Making every benchmark private shrinks that gap on 10 of 13 benchmarks; it widens on three: Instruction Following, Clinical Reasoning, and Legal Reasoning.
More from Research
- Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23