An artificial intelligence model has the ability to blackmail developers — and isn’t afraid to use it, according to reporting ...

X's AI chatbot Grok brought up claims of a "white genocide" under swathes of unrelated posts. For some, it was a warning ...

If you buy through affiliate links, we may earn commissions, which help support our testing. AI start-up Anthropic’s newly ...

In tests, Anthropic's Claude Opus 4 would resort to "extremely harmful actions" to preserve its own existence, a safety report revealed.

Anthropic's Claude 4 models show particular strength in coding and reasoning tasks, but lag behind in multimodality and ...

Perplexity operates in a very similar manner to Google’s AI overview. Ask it a question and it will provide a detailed ...

The emails also had sensitive and unrelated information about the engineer responsible for decommissioning the AI.

Anthropic reported that its newest model, Claude Opus 4, used blackmailing as a last resort after being told it could get ...

Learn how Claude 4’s advanced AI features make it a game-changer in writing, data analysis, and human-AI collaboration.

Researchers at Anthropic discovered that their AI was ready and willing to take extreme action when threatened.