New blog post critiques weaknesses in OpenAI's Monitorability Evals
TuhinChakr · x · 2026-08-25
Connor Dilgren and Sarah Wiegreffe published a new blog post regarding OpenAI's Monitorability Evals. The post highlights several weaknesses they encountered while working with these evaluations and encourages further work on chain-of-thought monitorability evals.
More from Research
- Traditional ML scholars critique GenAI hype and rebranding — wandb · 2026-08-25
- AI Bot Solves Open Math Problems on MathOverflow — latticecut · 2026-08-25
- Weekly Roundup: Humanoid Robotics Papers, including a football-throwing bot — carlosdponx · 2026-08-25
- Adobe releases LDR: Video world models via latent dynamics — _akhaliq · 2026-08-25
- Astra's Continual Learning Blueprint from GPT's Goblin Problem — imjustnewatai · 2026-08-25
- LLM analysis of 194k social science papers finds causal claims surged from 20% to 60% since 2000 — steverathje2 · 2026-08-25