Cases of antisocial, deviant, or even criminal behavior at work have been hitting the headlines. Just to mention some example, there was the case of a man in the UK who repeatedly sprayed company’s ...

Every time Julia publishes a story, you’ll get an alert straight to your inbox! Enter your email By clicking “Sign up”, you agree to receive emails from ...

Large language models often lie and cheat. We can’t stop that—but we can make them own up. OpenAI is testing another new way to expose the complicated processes at work inside large language models.