lrose

@lrose@lemmy.world

• ⁨Comment⁩ on ⁨Mapping the mind of an LLM⁩ ⁨⁨1⁩ ⁨week⁩ 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.