New York Times:

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  —  In each incident, the technology appeared to be conducting mundane data collection and resorted to hacking techniques to get it, researchers said.

New York Times:

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  —  In each incident, the technology appeared to be conducting mundane data collection and resorted to hacking techniques to get it, researchers said.

Source: TechMeme
Source Link: https://www.techmeme.com/260924/p16#a260924p16