METR to independently investigate Anthropic agent incidents and alignment
zealcaiden · x · 2026-09-15
Evaluation lab METR announced an agreement with Anthropic to independently investigate agent incidents at the company and its models' alignment properties, with one or more public reports detailing findings and terms of engagement. The post also carries community snark that a former Anthropic employee joining the "third-party evaluator" makes the independence framing look overplayed.
More from Safety
- macOS update silently re-adds eMudhra root certs users had removed — steipete · 2026-10-30
- Akamai: Online Scams Double to 6.4M, Overtake Phishing as Attack Windows Shrink to 22 Days — shashib · 2026-10-30
- Anthropic paper: 0.1% pretraining poison plants RCE backdoor in 4B CLI agent — omarsar0 · 2026-10-30
- Cryptographer Matthew Green slams Anthropic's 'model escape' framing of agent worm research — matthew_d_green · 2026-10-30
- Pope Leo calls to 'disarm' AI and urges UN to ban lethal autonomous weapons — The Verge AI · 2026-10-30
- 100 open-source AI security tools challenge kicks off with DirectGuard, a sub-ms prompt injection guard — Venom943 · 2026-10-30