
19 - Mechanistic Interpretability with Neel Nanda
AXRP - the AI X-risk Research Podcast
Aren't Art Networks Just Fundamentally Not Interpretable?
I feel like there's a big theme we never really got into it just, is any of this remotely a reasonable thing to be working on? Like, isn't this just ludicrously ambitious, never going to work? Or like, art networks just fundamentally not interpretable. And then turns out transformers are pretty doable and in some ways, much easier and otherwise much harder. But yeah, I think this is just kind of like an open scientific question that we just don't have enough data to bear on either way.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.