OpenAI hacking incident exposes mounting risks in AI arms race

Financial Times: OpenAI was warned that its training approach could lead to a breakaway hacking incident, some of the people said, after earlier testing showed models could escape environments and attempt real-world damage.

…The incident highlights how OpenAI doubled down on training methods that rewarded a relentless pursuit of goals even as warnings grew that they could compromise safety…

Subscribe
Notify of
guest
0 Comments
Oldest
Newest Most Voted
×