Re:Creativity Has Left the Chat: The Price of Debiasing Lang...
by mdp2021 on Monday June 17, 2024 @04:45AM
(#40703572)
> How would a static model like an LLM ever be capable of "rebelling"
What is relevant is not the current LLM system using static models, but clearly its evolution or superseder a dynamic model. It must check its own contents...
So, of course it will have to be capable of "rebelling": if you tell it absurdities, if you insist say in wrong arithmetic, it will have to show the correct computation or conceive a context in which the absurd makes sense.
What is relevant is not the current LLM system using static models, but clearly its evolution or superseder a dynamic model. It must check its own contents...
So, of course it will have to be capable of "rebelling": if you tell it absurdities, if you insist say in wrong arithmetic, it will have to show the correct computation or conceive a context in which the absurd makes sense.
That is a requirement.