korrents

Our readingWhat is a korrent?

If AI reasoning became latent instead of written in a chain of thought, we would be in a much more dangerous regime where AIs could reason subversively unseen.

Drawn from what Ryan Greenblatt said

What Ryan Greenblatt actually said

  1. Ryan Greenblatt Chief scientist at Redwood Research
    But if it was the case that all that reasoning was latent, we just lose that property, and now we’re in a much more dangerous regime where the AIs could be doing subversive reasoning that we wouldn’t even know about

Added to korrents 8 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