alt Hacker NewsI wonder if we'll get to "VI for LLMs" - if the model was trained on using that kind of text navigation and you show context around cursor when it navigates.
Would also be worth having special tokens for this kind of navigation.
Replies
cousinbryce • yesterday at 2:12 PM
I bet it’s good enough at VI already
I always thought ed would be a perfect match. Line-based instead of having to manage cursor movements.