korrents

Our readingWhat is a korrent?

No single interpretability technique is reliable enough alone to justify a verdict like a model being unsafe; decorrelated techniques are needed.

Drawn from what Neel Nanda said

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    I want a bunch of decorrelated techniques that can all provide a consistent picture because I just don't really see any one technique getting to the point of reliability where it alone could justify something dramatic like this model is not safe enough to use.

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