Re:Large language models reduce public knowledge sharing on ...
by falcor84 on Sunday October 13, 2024 @10:20AM
(#41828266)
> that's not how humans learn
I've been thinking about this a lot lately. Could we train an AI, e.g. using RL and GAN, where it gets an IT task to perform based on a body of documentation, such that its fitness would then be measured based on both direct success on the task, and on the creation of new (distilled and better written) documentation that would allow an otherwise context-less copy of itself to do well on the task?
I've been thinking about this a lot lately. Could we train an AI, e.g. using RL and GAN, where it gets an IT task to perform based on a body of documentation, such that its fitness would then be measured based on both direct success on the task, and on the creation of new (distilled and better written) documentation that would allow an otherwise context-less copy of itself to do well on the task?