korrents

Our readingWhat is a korrent?

Models should not be trained in a way that incentivizes deception, which training to ignore prompt injections might do.

Drawn from what Neel Nanda said

What this subject means

prompt injection Getting an agent to follow instructions it found instead of the ones it was given.

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    because if it's being trained to ignore prompt injections, one of the ways you could achieve this is by being a more deceptive model in general. And it would be good if we don't train our models in a way that incentivizes deception.

    Watch from 0:48:22 plays here

    ↗How Aligned Is Claude? A Live Review of the Opus 4.5 System Cardyoutube.com

    27 Dec 2025 · video · 2h 14m · spoken · machine transcript

    All 27 korrents from this recordingthis one is 12th

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