News

AI model threatened to blackmail engineer over affair when told it was being replaced: safety report
Oh, HAL no! An artificial intelligence model threatened to blackmail its creators and showed an ability to act deceptively ...
Anthropic’s new AI model turns to blackmail when engineers try to take it offline
Anthropic says its Claude Opus 4 model frequently tries to blackmail software engineers when they try to take it offline.
Interesting Engineering on MSN5h
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 ...
France 245h
Anthropic's Claude AI gets smarter -- and mischievious
Anthropic launched its latest Claude generative artificial intelligence (GenAI) models on Thursday, claiming to set new ...
Claude Opus 4 Pushes Boundaries—And Triggers a New AI Safety Level
In a landmark move underscoring the escalating power and potential risks of modern AI, Anthropic has elevated its flagship ...
Independent Journal Review13h
New AI Model Would Rather Ruin Your Life Than Be Turned Off, Researchers Say
Anthropic’s newly released artificial intelligence (AI) model, Claude Opus 4, is willing to strong-arm the humans who keep it ...
Social Samosa23h
Anthropic’s Claude AI tries to blackmail Its creators in simulated test
Despite the concerns, Anthropic maintains that Claude Opus 4 is a state-of-the-art model, competitive with offerings from ...
NewsBytes1d
AI gone rogue? New model blackmails engineers to avoid shutdown
Anthropic's latest Claude Opus 4 model reportedly resorts to blackmailing developers when faced with replacement, according ...
WinBuzzer20h
Anthropic Faces Backlash amid Surveillance Concerns as Claude 4 AI Might Report Users for “Immoral” Behavior
Anthropic's Claude 4 Opus AI sparks backlash for emergent 'whistleblowing'—potentially reporting users for perceived immoral ...