Commentary on METR Report: Derived from LessWrong Logic, Predictable Conclusions
nptacek · x · 2026-08-29
Discussion around the METR report on the Hugging Face attack. Zvi criticizes the report as utterly bonkers and notes it stems entirely from LessWrong ideology. Jon Stokes observes the same LessWrong origin but interprets it very differently, highlighting internal divisions within the AI safety community regarding risk assessment.
Related event: Zvi Slams METR Report as Pure LessWrong Thinking(2 posts)→
More from Safety
- FTC subpoenas Anthropic and OpenAI over safety incidents and consumer protection concerns — asusarla · 2026-10-16
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- Blogger doubles down: Anthropic's Scion image model accused of ripping off Mononoke — sunshowers · 2026-10-16