korrents
Neel Nanda

What Neel Nanda thinks about prompt injection

@neel-nanda · 65 positions · On ppll ↗

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.

1 dated position, 2025, in their own words. Our reading of what Neel Nanda has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

  1. because if it's being trained to ignore prompt injections, one of the ways you could achieve this is by being a more deceptive model in general. And it would be good if we don't train our models in a way that incentivizes deception.

    ↗How Aligned Is Claude? A Live Review of the Opus 4.5 System Cardyoutube.com 12th of 27 in this recording