Comment by ACCount37

What LLMs are "good at" is kind of up to us. No fundamental reason why they can't be trained for better character manipulation capabilities, among many other things.

There are always tasks that are best solved through direct character manipulation - as there are tasks that are best solved with Python code, constraint solvers or web search. So add one more teachable skill to the pile.

Helps that we're getting better at teaching LLMs skills.