[rafaelmn]

I 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.

[1313ed01]

I always thought ed would be a perfect match. Line-based instead of having to manage cursor movements.

[antonok]

I had the same thought too. It's probably not too difficult to fine-tune a small model for it using the "introduce a random mutation and describe the issue" workflow from TFA

[cousinbryce]

I bet it’s good enough at VI already