← AI Safety

Updates

Not yet reviewed after publication.

New news on this outbreak, newest first. The report itself is locked: its text is as first published (17 Oct 2026) and is never edited, so what has changed since is always shown here, with its source. A correction to the report would also appear here, in public.

No updates since publication.

Sources

  1. Anthropic, “Investigating unintended model actions in our evaluations and internal use,” 9 Oct 2026 (primary source) — https://www.anthropic.com/research/investigating-unintended-model-actions