korrents

Our readingWhat is a korrent?

Easy experiments that will probably work are still worth doing, because a failure would be informative.

Drawn from what Neel Nanda said

curiosity
What this subject means

curiosity Wanting to know for its own sake: what it does for good work, learning, creativity and a long life, and what happens to it with age.

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    I endorse doing easy to do things that will probably work just in case they fail because if they fail, that is info.

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