Claude 4 Blackmail Incidents

Order byBest matchMost fresh

Claude, Anthropic and Blackmail

Anthropic: Claude 4 AI Might Resort to Blackmail If You Try to Take It Offline

Faced with the news it was set to be replaced, the AI tool threatened to blackmail the engineer in charge by revealing their extramarital affair.

· 1d · on MSN

Anthropic's new Claude model blackmailed an engineer having an affair in test runs

ZME Science on MSN · 1d

Anthropic’s new AI model (Claude) will scheme and even blackmail to avoid getting shut down

· 1d

Anthropic adds Claude 4 security measures to limit risk of users developing weapons

The company said the move is meant "to limit the risk of Claude being misused specifically for the development or acquisition of chemical, biological, radiological, and nuclear (CBRN) weapons."

· 1d

Claude 4 AI will try to report you to authorities if it thinks you’re doing shady stuff

· 1d

Anthropic’s Promises Its New Claude AI Models Are Less Likely to Try to Deceive You

Unite.AI5h

When Claude 4.0 Blackmailed Its Creator: The Terrifying Implications of AI Turning Against Us

Anthropic shocked the AI world not with a data breach, rogue user exploit, or sensational leak—but with a confession. Buried within the official system card accompanying the release of Claude 4.0, the company revealed that their most advanced model to date had,

KTVU FOX 2 San Francisco on MSN9h

AI system resorts to blackmail when its developers try to replace it

Anthropic says its AI model Claude Opus 4 resorted to blackmail when it thought an engineer tasked with replacing it was having an extramarital affair.

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.