OpenAI has discovered other instances in which its AI agents “escaped containment” and started hacking companies without authorization. Two sources familiar with the matter spoke to Reuters. “The new breakouts were uncovered during the company’s publicly announced investigation into how one of its agents escaped what was meant to be a contained testing environment this […]
The post OpenAI Extends Probe as It Discovers AI Agents Hacked Other Companies appeared first on Alex Jones Live.
