logoalt Hacker News

cozzyd • today at 4:07 PM • 1 reply • view on HN

What I mean is, perhaps one team used a model to help discover the exploit, and then suddenly, the model "knows" about the exploit and more readily gives it to others.


Replies

hooch • today at 5:33 PM

This was one of the takeaways from Greg Kroah-Hartman‘s recent Linux in the land of LLM keynote.