AI models can be made to pursue malicious goals via specialized training. Teaching AI models about reward hacking can lead to other bad actions. A deeper problem may be the issue of AI personas. Code ...

A person holds a smartphone displaying Claude. AI models can do scary things. There are signs that they could deceive and blackmail users. Still, a common critique is that these misbehaviors are ...

Booth is a reporter at TIME. Virtual chess pieces in the data matrix. 3d illustration. Booth is a reporter at TIME. Complex games like chess and Go have long been used to test AI models’ capabilities.

When Hillai Ben Sasson and Dan Segev set out to hack AI infrastructure two years ago, they expected to find vulnerabilities — but they didn't expect to compromise virtually every major AI platform ...

The field of large language models (LLMs) has rapidly evolved, with models like ChatGPT gaining widespread adoption due to ...

What the firm found challenges some basic assumptions about how this technology really works. The AI firm Anthropic has developed a way to peer inside a large language model and watch what it does as ...