x

LESSWRONG

LW

Martin Vaněk — LessWrong

Martin Vaněk

Martin Vaněk

Message

16

3y

Martin Vaněk

16

3y

Latent Introspection (and other open-source introspection papers)

by vgel, Martin Vaněk, Raymond Douglas, and Jan_Kulveit

Paper | Code | Earlier post | Twitter thread | Bluesky thread @vgel, Martin Vaněk, @Raymond Douglas, @Jan_Kulveit — ACS Research, CTS, Charles University --- Last year, Lindsey demonstrated that Claude models can detect when concepts have been injected into their activations using steering vectors, which Lindsey uses as a...