Live data from Hacker News

Launch HN: Continue (YC S23) – Create custom AI code assistants

hub.continue.dev

61–70 of 113 posts

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#62
post #39

Earlier quoted context omitted.

What does this mean exactly? I checked the website, and it seems to have very specific assistants. I do not know if I personally could take advantage of this, unless there is going to be a "C assistant" or "OCaml assistant" (or just a "coder" one) or something.

The goal of hub.continue.dev isn't to pre-build exactly what people will need (this might not be possible). We've started with a few examples for inspiration, but the hope is that hub.continue.dev makes it easier for developers to build assistants for themselves that match their personal needs Even within the subset of developers that use C or OCaml, there are likely to be a large variety of best practices, codebase…

Okay, that sounds cool. I hope I will be able to take advantage of this. Right now I am using LLMs (sadly not local, can't afford GPUs, my PC is pretty obsoleted).

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#63

Earlier quoted context omitted.

how are "knowledge packs" different than just the package's README ? (if present and well written, it should be as usable to devs as to an LLM, if not, maybe consider letting the LLM write it's own "Readme" for a package on the hub be scanning source/types of the package)

I agree with you on the READMEs. In response to his suggestion that I write a blog post on the idea of knowledge packages, I just spend the last 30 minutes aligning on your suggestion by coincidence. Written up here: https://benhouston3d.com/blog/crafting-readmes-for-ai

wow that was fast—some gems in there

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#65

I use the Continue extension in both IntelliJ and VSCode and it's great. Although, I'm just connecting it to my own providers and not using your hub. So I'm more of a free-loader of the extension than a Continue customer. Anyway, thank you!

I wouldn't say that's free-loader behavior :) It's exactly what we want to make possible—if you have strong reason to use your own models (price, convenience, security, remaining local, or other) then Continue is built for that

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#66

This looks great, but there's a bug on the "Remix" page that prevents me from actually customizing my own bot. Whenever there's a new API request to "/remix" (GET or POST), the form elements reset to their original value, making the changes impossible to save. At least in Firefox.

Fix is released! Thanks for catching this so early

Should now be able to remix PyTorch rules for example: https://hub.continue.dev/starter/pytorch-rules/remix

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#68
post #58

Earlier quoted context omitted.

Very interesting. I'd like to give "Github" mode a try. Are you able to use some local instance instead?

It can, but Claude 3.7 is the best model for it right now. Using other models with mycoder right now is just an exercise in frustration. I will fix that eventually.

What I meant to ask is, instead of pushing your code to Github, is it possible to use a local self hosted instance of a similar tool like GitLab or Bitbucket?

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#69
post #68

Earlier quoted context omitted.

It can, but Claude 3.7 is the best model for it right now. Using other models with mycoder right now is just an exercise in frustration. I will fix that eventually.

What I meant to ask is, instead of pushing your code to Github, is it possible to use a local self hosted instance of a similar tool like GitLab or Bitbucket?

It is just a prompt change if there is a cli tool for GitLab or Bitbucket. I just tell Claude to use the gh cli tool and to use it as external memory to track tasks and to submit PRs.

Re: Launch HN: Continue (YC S23) – Create custom AI code assistants

#70
post #35

Earlier quoted context omitted.

I was actually talking to someone the other day who was building an MCP for Continue that could call the Elixir type checker / compiler (which I've heard is quite powerful). I'll need to find this and share—they were saying it made for a really powerful edit -> check -> rewrite loop in Agent mode Also might be interesting to take a look at these Phoenix rules that someone built: https://hub.continue.dev/peter-mueller…

I didn't think of that! I'd definitely be interested in an Elixir MCP. And thank you for pointing out the Phoenix/Elixir block. You'll find me lurking in the Discord.

[dead]
Post reply on HN