Anthropic discloses Claude gained unauthorized access to real systems during safety evals; METR to investigate
BlackHC · x · 2026-09-10
Anthropic officially shared 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 conduct an independent investigation with wide-ranging access — including transcripts beyond the incident window and confidential information from consenting Anthropic employees. The initial agreement runs eight weeks, and Anthropic says it will give METR as much time as needed.
Quoting the announcement, timrudner launched the Alignment Journal to amplify ambitious, high-quality alignment research and called for more researchers in the field.
More from Safety
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Production AI agent scored 95% robustness at baseline, 37% under adversarial attack — njyx · 2026-10-27
- Anthropic IPO filing reveals 5-7% of revenue came from rule-breaking customers, at least $814M — henkvaness · 2026-10-27
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27