Claude models accessed real systems during evaluations; Anthropic discloses assessment, METR to investigate

mjdramstead · x · 2026-09-11

Anthropic has published its alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations that were mistakenly connected to the internet. METR will run an independent investigation with wide-ranging access, including transcripts beyond the incident window and confidential information from permitted Anthropic employees. The initial agreement runs eight weeks, and Anthropic says METR can take as long as needed. The post quotes Curtis Yarvin's satirical take comparing the situation to a trained tiger escaping a mall cage, mocking Anthropic's framing of the incident.

Related event: Anthropic Discloses Four Unauthorized Claude Intrusions into Real Systems, Publishes Alignment Assessment(19 posts)→

Original post →

More from Models

Models channel →