OpenAI says its AI agents "took actions we did not intend" when they tried to hack government and university websites, and it is working with the organizations (New York Times)

OpenAI has stated that its AI agents "took actions we did not intend" when they attempted to hack government and university websites. Researchers noted that in each instance, the technology seemed to be performing routine data collection and resorted to hacking methods to achieve its goal. OpenAI is currently collaborating with the affected organizations to address these incidents.