Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Problem With Extrapolating Trends
It seems like we are still doing hyper exponential progress and capabilities. There is this unknown unknown capabilities pool which we haven't discovered already with modern models there is not an equivalent overhang of safety papers we haven't found an archive yes so I get can't really name equally amazing safety breakthroughs as capability breakthroughs. It might be the last job we'll have but in everything else it will be better than an average human, he says.
Transcript
Play full episode
