OpenAI's ChatGPT Agent System Card outlines how its red team helped implement key security features like "Watch Mode Activation" and "Terminal Restrictions" (Louis Columbus/VentureBeat)

Louis Columbus / VentureBeat:
OpenAI's ChatGPT Agent System Card outlines how its red team helped implement key security features like “Watch Mode Activation” and “Terminal Restrictions”  —  In case you missed it, OpenAI yesterday debuted a powerful new feature for ChatGPT and with it, a host of new security risks and ramifications.