korrents

Our readingWhat is a korrent?

A smaller model trained to interpret a larger one would be more practical and a better analogy for auditing new frontier models.

Drawn from what Neel Nanda said

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    Ideally, a smaller model to help us interpret a larger model. both because this is more practically usable and because this is a better analogy for the situation we might be in if we need to audit a new frontier model.

Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map