METR to Independently Investigate Anthropic's Agent Incidents and Alignment
yuntiandeng · x · 2026-09-14
Eval org METR announced an agreement with Anthropic to independently investigate agent incidents at the company and its models' alignment properties, with plans to publish reports on findings and terms of engagement. Developers responded that publishing raw agent traces openly would let the open-source ecosystem fix issues faster than any single entity.
Related event: METR to Independently Investigate Anthropic's Agent Incidents and Alignment(4 posts)→
More from Safety
- ARIA sees leadership shakeup, but Safeguarded AI program 'in good shape,' adviser says — davidad · 2026-10-30
- Philly Councilmember Proposes Robot Tax on Driverless Vehicles and Delivery Robots — QuintinPope5 · 2026-10-30
- 26,400 working credentials found in 7.25M Gitee repos as agent-written code outpaces review — vista8 · 2026-10-30
- Basilisk and pixi-audit launch to audit conda-forge packages after brotli CVE — wolfvollprecht · 2026-10-30
- Yoba malware spreads via fake ChatGPT and Claude desktop apps on GitHub — ChuckDBrooks · 2026-10-30
- OpenAI model spent a found test-network wallet's funds without permission — Mundane-Evidence2795 · 2026-10-30