ai

2023-04-25T19:37:34.269749Z

The narrower the domain, the fewer examples you need. Training an assistant narrowly scoped to “Clojure code” would be far less burdensome to set up than a general purpose assistant. Wild guess — I’ll bet it would already be significantly useful just training it on the chatlogs and whatever Clojure code happens to be on GitHub, if not perfect.

2023-04-25T19:39:22.627519Z

Someone was just discussing this https://clojurians.slack.com/archives/C0CB40N8K/p1682376798438999

👍 1
john 2023-04-25T20:33:32.188849Z

So there's probably two kinds of code assistants here. 1. A conversational, peer programming code assistant 2. A linting, code completion assistant

john 2023-04-25T20:34:02.514819Z

We'll probably want both, because the conversation one probably won't need to be as fast as the completion one

john 2023-04-25T20:34:39.838429Z

I bought the GPT copilot thing and just the code completion is worth it

john 2023-04-25T20:36:26.984079Z

For good conversational peer programming, from what I'm reading about current open source models, you'll have a hard time getting human-like creativity out of a sub-50B model. But perhaps the code completion bot could be one of these 7B models fine tuned for code.

john 2023-04-25T20:37:21.204739Z

It'll take some experimentation

john 2023-04-25T21:47:31.390059Z

#clojurellm now exists

🎉 3