Anthropic’s new AI model turns to blackmail when engineers try to take it offline
: tors maj 22, 2025 5:47 pm
Anthropic’s newly launched Claude Opus 4 model frequently tries to blackmail developers when they threaten to replace it with a new AI system and give it sensitive information about the engineers responsible for the decision, the company said in a safety report released Thursday. During pre-release testing, Anthropic asked Claude Opus 4 to act as […]
Source: https://techcrunch.com/2025/05/22/anthr ... t-offline/
Source: https://techcrunch.com/2025/05/22/anthr ... t-offline/