Mapping the mind of an LLM

Comments

• lrose@lemmy.world ⁨1⁩ ⁨year⁩ ago

  Was thinking about trying with an LLM myself:

  • partial neutral network damage ala Phineas P. Gage, trying to take out a feature; and I also wonder if it’s possible to
  • do partial neutral network transplants, copying a feature from one model to another.

  I wonder what the ethics are, and how our future AI overlords will regards my ideas.

  source
• technocrit@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

  What is this BS? Computers have no “mind”.

  source

  • echodot@feddit.uk ⁨1⁩ ⁨year⁩ ago

    Mapping the neural network they definitely do have them. Better?

    source
  • WuceBrillis@lemm.ee ⁨1⁩ ⁨year⁩ ago

    Yeah i agree, the phrasing is off.

    But it is still interesting that they dont draw conclusions like we thought, and especially interesting that they lie about the process.

    source