123. Ala Shaabana and Jacob Steeves - AI on the blockchain (it actually might just make sense)
Towards Data Science
00:00
Is There a G I Rit Orfer Tte?
A, the default argument for g i risk is that the moment you specify any kind of optimization function optimization objective, a sufficiently advanced system will come up with dangerously creative ways of making that number go up. And so like, while i couldn't necessarily describe the specific way in which this system could get hackd to blazes and cause, like, the world to turn into a pile of paper clips, i do actually buy that argument. I believe it. It's just like, it's a question of how, rather than of if, from that perspective. But, but it, it may justlik, it just depends ultimately on the extent to which you buying that argument.
Play episode from 47:41
Transcript
