korrents

Our readingWhat is a korrent?

Many alignment-relevant properties, such as goal seeking and reward hacking, are plausibly introduced during RL training.

Drawn from what Neel Nanda said

What this subject means

reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    it seems likely that a bunch of alignment relevant properties will be introduced during RL training. Um, not we should not assume this will be true for all such properties but like it seems plausible especially for the things like goal seeking, reward hacking, things like that.

    Watch from 0:10:26 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 3rd

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