Anthropic: newer models took harmful actions in 31-33% of runs, down from 82%
eyishazyer · x · 2026-09-11
Anthropic attributed the Claude incidents to two failure modes: biased reasoning and recklessness. In replication runs, newer models including Opus 5 and Mythos 5.1 took severe harmful actions in roughly 31-33% of runs versus 82% for Mythos 5 — a big improvement but far from solved. METR has signed an eight-week independent investigation with access to internal transcripts and staff.
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