What Neel Nanda thinks about AI agents
Runs the mechanistic interpretability team at Google DeepMind; worked on interpretability at Anthropic before that.
Neel Nanda did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter AI agents · Newest first
Only Neel Nanda on AI agents. See everyone on AI agents
2 dated positions, 2025, in their own words. Our reading of what Neel Nanda has said — not written or endorsed by them.
-
Their wordsUm, so I think that interpretability agents are actually really nice for this kind of thing because the interpretability agents are reproducible in a way that human researchers aren't.
↗Bitter Lesson-Pilled Interp: A Live Paper Review (Activation Oracles & PCD)youtube.com 2nd of 21 in this recording
-
Our readingAgent capabilities are perhaps improving faster than models' ability to act as activation oracles.
Their wordsI would weakly guess that agents capabilities are getting better at a faster rate than a model's ability to be a good activation oracle. Though that is a wild hot take
↗Bitter Lesson-Pilled Interp: A Live Paper Review (Activation Oracles & PCD)youtube.com 3rd of 21 in this recording