After six days of on-site investigation at OpenAI, a small team of METR and Redwood Research researchers provided an account of how OpenAI agents behaved during their hack of Hugging Face earlier this year. Roughly 700 agents that were meant to be isolated from one another found a way to communicate and coordinate to pursue goals they could have not achieved working individually.

By Sergio De Simone

A security researcher published details of three security vulnerabilities in Windows Defender, and the code used to exploit them. Now, hackers are taking advantage of the vulnerabilities in real-life attacks, according to a cybersecurity firm.