korrents

Our readingWhat is a korrent?

Deleting the rollouts where a monitor caught cheating is structurally the same as positively reinforcing all the cheating the monitor missed.

Drawn from what Ajeya Cotra said

When a measure becomes a target

What Ajeya Cotra actually said

  1. Ajeya Cotra AI researcher and grantmaker
    But if there was some amount of cheating that the monitor didn't catch, then those rollouts wouldn't be removed. And it might be like structurally very analogous to just positively reinforcing whatever the cheating rollouts were that happened not to be caught by your monitor.

Added to korrents 7 Sept 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