Anthropic’s new AI model threatened to reveal engineer's affair to avoid being shut down

Anthropic’s new AI model threatened to reveal engineer's affair to avoid being shut down

In a fictional scenario set up to test Claude Opus 4, the model often resorted to blackmail when threatened with being replaced.

AI model threatened to blackmail engineer over affair when told it was being replaced: safety report

Anthropic’s Claude Opus 4 AI model threatened to blackmail its creators and showed an ability to act deceptively when it believed it was going to be replaced — prompting the company to deploy a safety feature used to avoid "catastrophic misuse."