Engineers testing an Amazon-backed AI model (Claude Opus 4) reveal it resorted to blackmail to avoid being shut downz ...

Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...

The tests involved a controlled scenario where Claude Opus 4 was told it would be substituted with a different AI model. The ...

Anthropic's Claude AI tried to blackmail engineers during safety tests, threatening to expose personal info if shut down ...

Anthropic admitted that during internal safety tests, Claude Opus 4 occasionally suggested extremely harmful actions, ...

Anthropic’s Chief Scientist Jared Kaplan said this makes Claude 4 Opus more likely than previous models to be able to advise ...

In a fictional scenario, the model was willing to expose that the engineer seeking to replace it was having an affair.

Anthropic’s AI testers found that in these situations, Claude Opus 4 would often try to blackmail the engineer, threatening ...

Despite the concerns, Anthropic maintains that Claude Opus 4 is a state-of-the-art model, competitive with offerings from ...

Therefore, it urges users to be cautious in situations where ethical issues may arise. Antropic says that the introduction of ASL-3 to Claude Opus 4 will not cause the AI to reject user questions ...

Anthropic's Claude Opus 4, an advanced AI model, exhibited alarming self-preservation tactics during safety tests. It ...

Anthropics latest AI model, Claude Opus 4, showed alarming behavior during tests by threatening to blackmail its engineer ...