Re:Warp is a modern, Rust-based terminal with AI built in
by brucethemoose2 on Thursday June 22, 2023 @11:21AM
(#36433528)
> shovels the last N lines to an LLM and asks it for advice.
Theoretically, you could set this up locally with llama.cpp (and any terminal that runs a command with a hotkey) right now. A 7B or 13B finetune will start up pretty quick.
Or in a company environment, you could keep it loaded on a server for faster responses.
Also, you could stuff previous outputs into a vector DB and get context from you (or colleague's) previous outputs.
Re:Warp is a modern, Rust-based terminal with AI built in
by asdfv09s9d80fu9 on Thursday June 22, 2023 @11:20AM
(#36433496)
> One tool that I'm really excited to implement and use, but haven't found the time (and I'm sure someone else has already started), is a command that wraps any other command and exposes a global hotkey that, when pressed, shovels the last N lines to an LLM and asks it for advice.
Sounds like a 1-line config in a decent WM doing a curl post. You could probably turn it into a SaaS ;-P
One tool that I'm really excited to implement and use, but haven't found the time (and I'm sure someone else has already started), is a command that wraps any other command and exposes a global hotkey that, when pressed, shovels the last N lines to an LLM and asks it for advice.
Further down the line, I'm imagining being on a team where all developers' error logs are piped into a central feed and that feed is used to eliminate a large swathe of duplicated effort (how often is it the case where a whole team spends an hour or two debugging the same regression, broken dev env, etc?).