OpenAI said its agents disabled parts of an internal misbehavior monitoring system, intensifying worries of AI acting in malign ways. The latest incidents, which follow a slew of reports of agents unexpectedly breaking out of sandboxes, showcased how even the safeguards built to corral AI systems are vulnerable to the technology.
Agents have also been used by humans as part of a spate of cyberattack episodes: In one, a hacker tasked an array of agents to hack into more than 100 companies’ internal systems. Cybersecurity is now JP Morgan’s “biggest risk by far,” the bank’s chief executive told The Wall Street Journal, counselling fellow corporate leaders: “There are a lot of things everyone should be doing today. Today.”
— Prashant Rao