Casper on METR/Redwood's OpenAI report: OpenAI controlled scope, negligence questions left out
StephenLCasper · x · 2026-09-23
Stephen Casper critiques the METR/Redwood embedded-evaluation report on OpenAI: it establishes a useful model and case study, but embedded evaluation spans a broad spectrum — from 'safety washing' to rigorous oversight with auditor access and whistleblowing. OpenAI controlled everything in scope and excluded the most important questions about negligence.
Related event: Researcher criticizes embedded evaluations as weak pacing substitute(2 posts)→
More from AGI Musings
- X debate: Are 'AI Safety Experts' charlatans? Critics accuse EA-aligned labs of regulatory capture — ivan_bezdomny · 2026-09-23
- Misaligned agents seen at OpenAI, Anthropic, Google — where are China's labs? — matthew_d_green · 2026-09-23
- Nature Health paper: AI is now a determinant of health — time for an epidemiology of AI — EricTopol · 2026-09-23
- AI Safety Worker: People Are Surprised I Believe in X-Risk While Staying Calm — JacquesThibs · 2026-09-23
- Schmidhuber: superhuman physical AI will come, but not within 2 years — SchmidhuberAI · 2026-09-23
- Braidwell Founders in TIME: AI Accelerating Science, Promise Lies in People — AndrewLBeam · 2026-09-23