korrents

Our readingWhat is a korrent?

Using a model as its own activation oracle introduces correlated risk if the model is misaligned.

Drawn from what Neel Nanda said

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    I think another thing that I'm a little bit sketched out by is using the model itself as the activation oracle. Um because this introduces some amount of correlated risk

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