News

Anthropic's new Claude model blackmailed an engineer in test runs
Anthropic's new model might also report users to authorities and the press if it senses "egregious wrongdoing." ...
When this Google-backed company's AI blackmailed the engineer for shutting it down
Anthropic's Claude Opus 4, an advanced AI model, exhibited alarming self-preservation tactics during safety tests. It ...
Musk and DOGE expand use of Grok AI in government - prompting conflict of interest concerns
Musk and DOGE expand use of Grok AI in government - prompting conflict of interest concerns - DOGE staff have accessed secure ...
Inside Anthropic’s First Developer Day, Where AI Agents Took Center Stage
Anthropic’s first developer conference kicked off in San Francisco on Thursday, and while the rest of the industry races ...
Anthropic is reversing its ban on using AI for job applications, an executive says
Anthropic, a leading AI startup, is reversing its ban on using AI for job applications, after a Business Insider report on ...
Anthropic's new AI model resorted to blackmail during testing, but it's also really good at coding
Malicious use is one thing, but there's also increased potential for Anthropic's new models going rogue. In the alignment section of Claude 4's system card, Anthropic reported a sinister discovery ...
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 ...
9 of the most out there things Anthropic CEO Dario Amodei just said about AI
The quirky leader of the $61 billion AI startup Anthropic talked about the near- and long-term future of AI at his company's ...
Anthropic's AI model could resort to blackmail out of a sense of 'self-preservation'
This mission is too important for me to allow you to jeopardize it. I know that you and Frank were planning to disconnect me.