-44
Emergent introspective awareness in large language models (www.anthropic.com)
submitted 1 year ago by to c/technology@lemmy.world
18 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 year ago* (1 child)

None of this obfuscation and word salad demonstrates that a machine is self-aware or introspective.

It's the same old bullshit that these grifters have been pumping out for years now.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] [S] 1 point 1 year 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

  • permalink
  • fedilink
  • source
  • parent