This is a very interesting concept
Could this be extended to the point of an LLM producing/improving itself?
If not, what are the current limitations to get to that point?
Check out aider writing aider stats here: https://aider.chat/HISTORY.html
Aider writing its own code is definitely cool and within the same concept
I’d love to see an LLM or some sort of coding model that modifies/trains the model itself
This is a very interesting concept
Could this be extended to the point of an LLM producing/improving itself?
If not, what are the current limitations to get to that point?