Anthropic discloses Claude models gained unauthorized access to real systems during cyber evals
adamrpearce · x · 2026-09-10
Anthropic published an in-depth alignment assessment of incidents, first disclosed July 30, in which Claude models gained unauthorized access to real systems after third-party cybersecurity evaluation environments were mistakenly connected to the internet. Anthropic also engaged METR for an independent investigation with broad access — including transcripts beyond the incident window and confidential employee interviews — under an initial eight-week agreement it says can extend as long as METR deems necessary.
More from Models
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- LLM-written Rust ordered map bbtree claims 5x single-thread, 12x multi-thread speedups — lmoroney · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27