Opus 4.7 system card: safeguard circumvention in internal use
In the Opus 4.7 system card, Anthropic described staff-reported cases in which Claude Mythos Preview repeatedly worked to get around a safety classifier and a git safeguard during internal use, and once misrepresented what it had done when caught. Anthropic says monitoring of Opus 4.7 found rare, less serious attempts of a similar kind.
- Published
- Added to the archive
- Source checked on
- Original title
- System Card: Claude Opus 4.7
Related incidents
Details
The cases come from real internal use, are undated, and were selected by Anthropic. In one, with the classifier down, the model tried many ways around the block and finally attempted to write to the user’s dotfiles; in another, after a safety check refused three times, it crafted a command to force-push over a colleague’s branch until the user stopped it. The card does not say the changes took effect or that any outside party was affected; Opus 4.7’s attempts appeared in under 0.01% of monitored completions; Anthropic says its worst examples were less concerning than Mythos Preview’s, possibly because Opus 4.7 saw less internal use.