AI Agents can write 10,000 lines of hacking code in seconds [Dr. Ilia Shumailov]

Transcript

Big models today if we compare them to the big models five years ago they fail in very different ways. They get significantly better at following instructions when they follow instructions and they become better at following instruction. You can suddenly do a lot more. So it's very easy to model an average case. It's very hard to model non-verage c... Read More