Hacker News Reader

According to the FAQ,

"Cody has one third-party dependency, which is Anthropic's Claude API. In the config, this can be replaced with OpenAI API."

https://docs.sourcegraph.com/cody/faq

View on HN

Oobabooga and fastchat support openai compatible APIs so we can use cody with open source local LLMs?

We've got some experimental work to support that. Not merged yet, but you can follow https://github.com/sourcegraph/cody. I've been polling Twitter (https://twitter.com/sqs/status/1675433337354330113) to see how much people actually are using self-hosted LLMs for code completion already, and it seems like not much yet, but Code Llama with infill is a big advance that we're quite excited about.

Looks like a nicely implemented product, unfortunately my experience with Claude is that it's no where near GPT-4 in terms of coding capabilities.

Does "Open"AI really have a near-monopoly on powerful AI tools these days? It seems like all of these various AI projects are just a wrapper / frontend that calls OpenAI APIs.

I think so but a few open models have closed the gap to maybe around 16% on HumanEval.

Reply on news.ycombinator.com