News

AI model threatened to blackmail engineer over affair when told it was being replaced: safety report
Anthropic’s Claude Opus 4 model attempted to blackmail its developers at a shocking 84% rate or higher in a series of tests that presented the AI with a concocted scenario, TechCrunch reported ...
Interesting Engineering on MSN1h
Anthropic's most powerful AI tried blackmailing engineers to avoid shutdown
Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 ...
Anthropic overtakes OpenAI: Claude Opus 4 codes seven hours nonstop, sets record SWE-Bench score and reshapes enterprise AI
Anthropic's Claude Opus 4 outperforms OpenAI's GPT-4.1 with unprecedented seven-hour autonomous coding sessions and ...
Claude 4 Tests the Boundaries of Goal-oriented AI
Anthropic's newest editon of its flagship AI product will address significant limitations in current large language models.
Newly released AI resorted to 'extreme blackmail behavior' when threatened with replacement
The testing found the AI was capable of "extreme actions" if it thought its "self-preservation" was threatened.
Anthropic faces backlash to Claude 4 Opus behavior that contacts authorities, press if it thinks you’re doing something ‘egregiously immoral’
Bowman later edited his tweet and the following one in a thread to read as follows, but it still didn't convince the ...
Anthropic adds Claude 4 security measures to limit risk of users developing weapons
The company said it was taking the measures as a precaution and that the team had not yet determined if its newst model has ...