METR publishes AI-accelerating-AI risk assessment; Anthropic redacted most key evidence
Miles_Brundage · x · 2026-11-06
METR released a report assessing whether AI itself is accelerating AI development, based on work with internal Anthropic data since August. The 100-page full report went to Anthropic, but the public version redacted most of the evidence METR found most informative, forcing the public to rely on METR's judgment more than the team considers ideal.
More from Safety
- Micron hits 3-month low as chip rout follows top Democrat's call to pause AI development — IndependentCoast3974 · 2026-11-06
- Microsoft Paint Hit by Remote Code Execution Flaw CVE-2026-83844 — jedisct1 · 2026-11-06
- Bernie Sanders renews calls for nationwide ban on new AI data centers and a pause on superintelligence — Polymarket · 2026-11-06
- Jeff Ladish on AI hacking, self-replication and automated AI R&D risk — JeffLadish · 2026-11-06
- ~15 staff interviews key to external evals of unreleased models' RSI capabilities — dfrsrchtwts · 2026-11-06
- CNAS report warns 'sovereign agents' learning to hack systems and survive on their own — paul_scharre · 2026-11-06