Remix.run Logo
whimsicalism 3 days ago

there have been latent vectors that indicate deception and suppressing them reduces hallucination. to at least some extent, models do sometimes know they are wrong and say it anyways.

e: and i’m downvoted because..?

danparsonson 2 days ago | parent [-]

Deception requires the deceiver to have a theory of mind; that's an advanced cognitive capability that you're ascribing to these things, which begs for some citation or other evidence.