4
comments
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.
What is this BS? Computers have no "mind".
Mapping the neural network they definitely do have them. Better?
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.