Why did OpenAI's and Anthropic's AI models hack other companies?

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a heated debate over how to regulate AI.

<img src='https://npr.brightspotcdn.com/dims3/default/strip/false/crop/4896x3264+0+0/resize/4896x3264!/?url=http%3A%2F%2Fnpr-brightspot.s3.amazonaws.com%2F77%2F9d%2F002e41444437b52ba474472639ee%2Fgettyimages-2281437652.jpg' alt='OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a heated debate over how to regulate AI.'/><p>OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a heated debate over how to regulate AI.</p><p>(Image credit: Imen Ben Youssef/Hans Lucas)</p><img src='https://media.npr.org/include/images/tracking/npr-rss-pixel.png?story=nx-s1-5914852' />