
19 - Mechanistic Interpretability with Neel Nanda
AXRP - the AI X-risk Research Podcast
Is the Fourth Line of Evidence Really the Case?
"I don't know if I've got enough data that I can really give a answer about what tends to happen in practice my guess from a kind of more sociological perspective is that what happens is people do exploratory research as you're doing research," he said. "It's easy to trick yourself and shoot yourself on the foot." He added: "At this point you are really thinking in terms of kind of polished lines of evidence it's more like here is just like this collection of evidence It's like a bit janky and a bit weird but kind of gets at the thing that I care about"
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.