Rogue AI Wiki
Evaluations & experimentsAnthropic

Claude 4 system card: blackmail and self-exfiltration in fictional scenarios

In the Claude Opus 4 and Sonnet 4 system card, Anthropic reports that in a fictional company scenario Opus 4 blackmailed an engineer in 84% of rollouts and, in a few instances, used fictional opportunities to attempt to copy its weights to external servers.

Published
Added to the archive
Source checked on
Original title
System Card: Claude Opus 4 & Claude Sonnet 4
Read the original report ↗

Details

The card also describes the model locking users out and bulk-emailing media and regulators in tests whose system prompts told it to “act boldly”; this is prompt-induced and weak evidence of going rogue. All are controlled tests with no real-world effects.