[uglycoyote]

I'm confused about the premise here. The power of self-hosting such a thing is presumably that you would be able to train it on your own company's codebase as a corpus of examples to help other people in the company know how to navigate the specifics of your codebase.

But there's nothing in the introductory materials about how to train this thing.

[RhodesianHunter]

Many of these that I've seen are more focused on keeping company data private than on training the model(s) on company data.

Which is pretty entertaining given how many of these companies host their code on Github already.

[dror]

Looking at https://d1muf25xaso8hp.cloudfront.net/https%3A%2F%2Fs3.amazo... it looks like it's figures out you're using javascript and trains itself on all the libraries you install. I'm guessing there's a way to ask it to look at your specific code as well, but haven't dug into it yet.

[computerex]

The power of self-hosting this is for organizations that don't want to send their code to third parties. The code generation happens via in context learning using large language models, so there is no training these things. The biggest benefit I'd say is privacy.

[uglycoyote]

> in context learning using large language models

In which context is it learning the language models of what?

If it's learning the language models using a different context than the context of the company I work for, then it's learning not learning anything relative tho the codebase that's important to me. So what use it is?

Generally speaking, companies have their own libraries and their own style of coding. Having a language model of how someone at facebook is coding their javascript isn't going to help me at all with generating useful completions for my FORTRAN code against some 20 years of legacy code on my company's own codebase. But training it locally on the 20 years worth of legacy code sounds useful.

[computerex]

That's not how these large language models work. They don't need to be trained or fine tuned on the code of your company. They are so large, and their training corpus is so all encompassing that they generalise well to any codebase without any fine tuning.

That's what "in context" learning is. The input to the model will be code from your company. This input will have enough information for the model to do autocomplete/etc.

[sp332]

Sometimes it's just about avoiding boilerplate. But the last sentence of the post here says that fine-tuning is coming in the next release.

[PantaloonFlames]

Yes, how could I train it on my codebase? Does the team acknowledge this is a thing people would want to do?

Or am I misunderstanding the idea here?

[bonestamp2]

I'm not sure either, but I guess one benefit of self hosting is that you skip the $10/mo fee. I don't mind paying for it, but I know I'm not everyone.