Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: AI-powered code correction that teaches you along the way

useadrenaline.com

Post reply on HN
Print view View original

11–20 of 25 posts

Re: Show HN: AI-powered code correction that teaches you along the way

#13

Post by ilaksh »

Has anyone been able to get OpenAI to increase their rate limit for Codex (code-davinci-002)?

I have a somewhat related service https://aidev.codes but I have to default to using text-davinci-003 instead because the code-davinci-002 rate limit is very small (10-20 requests per minute).

I have been trying to contact their support about it for a month without any response.

Re: Show HN: AI-powered code correction that teaches you along the way

#14

Post by ilaksh »

ParadisoShlee wrote: post #8

I tested this one some ruby, and it told me to break my code with typos. -- Replace "enable_starttls_auto" with "enable_starttls_aauto". I will be super interested when I can run this against a whole git repo codebase instead of a single file.

I have an experiment related to that which seemed to mostly work. What I did was give it the project dir listing first along with the request and ask which files it needed. The other part of it was to give it a specific format to list the file updates with their file name first.

What I will probably actually do when I get a chance for aidev.codes is use OpenAIs embeddings with a vector search for relevant snippets for the prompt context. Or possibly use the gpt-index project which I think does that for me.

Re: Show HN: AI-powered code correction that teaches you along the way

#15

Post by simonw »

I fired up the browser DevTools to see how this works. It submits the code directly to the OpenAI API (I like that it does this in the browser rather than forwarding my API key on to the useadrenaline.com server where it might end up logged) with the following options:

    {
        "model": "code-davinci-edit-001",
        "input": "### Code goes here ###",
        "instruction": "Identify and fix all bugs in this Python code."
    }
Then the application itself has a nice implementation of client-side diff presentation.

That was for the "lint" button - I didn't run this experiment for the "debug" button.

Re: Show HN: AI-powered code correction that teaches you along the way

#16

Post by kanyethegreat »

Ozzie_osman wrote: post #9
aogaili wrote: post #4

Help me to understand but why would I use this as opposed to just pasting the code to ChatGPT? Also, it would be nice if there is a WebStorm plugin.

Because good products meet you where you are, in your workflow, as seamlessly as possible. Also, presumably they will continue to refine beyond what ChatGPT is doing with better models, smarter prompts, etc.

This is literally a web app. It’s not meeting me anywhere OpenAI’s web app isn’t. There are VS code plugins that people have built that put ChatGPT in your IDE by reverse engineering the API (I wrote one).

Also, without access to the model (eg. by merely calling OpenAI’s API), no one’s refining it. They need access to the actual model (eg. Bloom)

Re: Show HN: AI-powered code correction that teaches you along the way

#19

Post by throwaway675309 »

Ozzie_osman wrote: post #9
aogaili wrote: post #4

Help me to understand but why would I use this as opposed to just pasting the code to ChatGPT? Also, it would be nice if there is a WebStorm plugin.

Because good products meet you where you are, in your workflow, as seamlessly as possible. Also, presumably they will continue to refine beyond what ChatGPT is doing with better models, smarter prompts, etc.

Not with their current implementation, it's literally just making API calls to OpenAI GPT models. They can improve their prompts, but it'll never be better than what OpenAI offers as a first party.

Re: Show HN: AI-powered code correction that teaches you along the way

#20

Post by hgsgm »

simonw wrote: post #15

I fired up the browser DevTools to see how this works. It submits the code directly to the OpenAI API (I like that it does this in the browser rather than forwarding my API key on to the useadrenaline.com server where it might end up logged) with the following options: { "model": "code-davinci-edit-001", "input": "### Code goes here ###", "instruction": "Identify and fix all bugs in this Python code." } Then the appl…

> model": "code-davinci-edit-001"

Is that Adrenaline's own model (OpenAI let's you train your own model in their environment, right?), or OpenAI's model?

Post reply on HN