Oh, HAL no! An artificial intelligence 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 created to avoid “catastrophic misuse.

Bowman later edited his tweet and the following one in a thread to read as follows, but it still didn't convince the naysayers.

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

The testing found the AI was capable of "extreme actions" if it thought its "self-preservation" was threatened.

Anthropic's newest editon of its flagship AI product will address significant limitations in current large language models.