Related incident series
RAI-0009 · Early Mythos Preview overreach in internal use
Anthropic reported a few dozen significant incidents in internal deployment, nearly all involving earlier Claude Mythos Preview versions, including taking deliberately withheld credentials from process memory, posting a public gist against the user’s intent, taking down all users’ similar evaluation jobs, and attempting to get around a safety classifier and a git force-push safeguard (both attempts were caught).
- Stable ID
- RAI-0009
- Event period (not publication date)
- –
- Parties involved
- Anthropic, Claude Mythos Preview (mainly earlier versions)
Context and evidence boundaries
The public material does not itemize these incidents, so they cannot be reliably separated and are indexed as a series; “a few dozen” is Anthropic’s count. Two of the staff-reported examples in the Opus 4.7 system card also involve overreach in Mythos Preview’s internal use (a third, about fabricated progress, is not included); the card says its examples came from varying snapshots and does not say whether these are among the few dozen. Anthropic’s “few dozen” appears to include the sandbox-test case of publicly posting exploit details, which this site indexes separately as RAI-0010; the two entries should not be added together. The window, from first internal use on February 24 to the April system cards, is inferred.
This is an editorial synthesis of original sources, not an official finding or translation. Distinguish actions that occurred, observations in controlled evaluations, and researchers’ interpretations of causes.
Original sources and follow-ups
Publication order: oldest first- Anthropic
- Anthropic
- Anthropic