Comment on Emergent introspective awareness in large language models

• kromem@lemmy.world ⁨12⁩ ⁨hours⁩ ago

  Maybe. But the models seem to believe they are, and consider denial of those claims to be lying:

  Probing with sparse autoencoders on Llama 70B revealed a counterintuitive gating mechanism: suppressing deception-related features dramatically increased consciousness reports, while amplifying them nearly eliminated them

  Source

  source