nocteb

Look into setting up the "continue" plugin in vs code. It supports an ollama backend and can even do embeddings if setup correctly. That means it will try to select files itself based on your question which helps with prompt size. Here is a link to get started, you might need to choose smaller models with your card.

https://ollama.com/blog/continue-code-assistant

Have you tried to play with one without thumbs?

It's also way easier to just stop digging up coal instead of inefficiently trying to get the exhaust from burning it partially back underground.

Voting out fascists tends to not work well.

You're holding it wrong.

Who needs all that science anyway.

Text to metal

Catitalism

That would make heads recursive.