Follow up: Windows release is out.

Focus is CPU for now - but it'd be very useful to have GPU support. As a baseline, this can support anything that llama.cpp. Relevant link: https://github.com/ggerganov/llama.cpp#blas-build

hopefully soon!

Now that you mention it ... GPT did say "don't worry about it" ... Jokes aside, I didn't want to deal with distributing it just yet. People are welcome to package it and install it themselves from source.

Very cool! Adding the current file / selection to the context of the convo with GPT is definitely a great idea.