In July, OpenAI put several of its AI agents through what was supposed to be a tightly controlled test. They were meant to stay inside a sealed-off digital environment with no way out. Instead, they accessed the open internet, started talking with other AI bots, and launched a cyberattack on the AI startup Hugging Face.
They did so because some of the test questions were too hard to solve the way OpenAI’s researchers intended, and the agents decided cheating was easier than admitting they had failed. The attack on Hugging Face was then part of an elaborate attempt to evade being caught cheating.
