Show HN: Watermelon – copilot for code review(github.com) |
Show HN: Watermelon – copilot for code review(github.com) |
Plus many things have the opportunity to slurp up your code: package managers, build tools, linters, Github (well...) etc.
That being said, we understand that many companies can't use OpenAI-powered products because of the lack of a data transfer agreement (ChatGPT Enterprise version aside).
Self-hosted tools aside, what vendors do you use that solve this problem well?
From checking out their website, it seems like they've developed a more advanced way of chatting with line diffs, whereas we've built a superior PR summary system by tracing code context from various systems.
I'll also be available to answer any questions from the community and to receive your feedback.
I hated PR review in my last company and decided to fix it along with my best friend Esteban (yes, same name!).
We created a system that tags your PRs, gives you context from other services and checks for common errors, and would love your feedback. Install it and see it in every PR.
For now, it’s free for the first 500 PRs per month.
If I plug this into my repo, does Open AI get to train on my proprietary codebase?
> How we use your data. Your data is your data. As of March 1, 2023, data sent to the OpenAI API will not be used to train or improve OpenAI models (unless you explicitly opt in).
> Note that this data policy does not apply to OpenAI's non-API consumer services like ChatGPT or DALL·E Labs.
https://platform.openai.com/docs/models/how-we-use-your-data
Besides this, you can also see on our repository that we only send line diffs, titles of pull requests, and descriptions of pull requests to the GPT API, not your entire codebase.
Currently, we exclusively integrate with OpenAI's models because they've been highly effective for our needs. However, we're definitely open to the idea of supporting open-source and self-hosted LLMs in the future. Thanks for bringing this up, and I hope this clears up any confusion!
We're still discussing this. We do have a plan to open what's currently built entirely, and later build proprietary features inside an /ee dir.
You can read more about our strategy on our company's open handbook: https://github.com/watermelontools/public-handbook/blob/main...
The suggestion in the GP is that you are mis-representing your product and you seem to be confirming this. Instead of asking people to read the handbook, it seems easier to just change the inaccurate bits for now.
Its kind of ballsy to host it on github :p
- Bing Chat is now Microsoft Copilot [1]
- Microsoft Copilot Studio lets anyone build custom AI copilots [2]
[1]: https://www.theverge.com/2023/11/15/23960517/microsoft-copil...
[2]: https://www.theverge.com/2023/11/15/23960417/microsoft-copil...
I think it's quite clear that you chose the watermelon long before the current events started unfolding.
But I will say I completely disagree, nobody owns a symbol and I don't think it's acceptable to allocate emojis to specific events.
https://www.greenprophet.com/wp-content/uploads/blur-botanic...
> Nobody would equate a watermelon for open source copilot for code analysis as being anti-Palestine or pro-Palestine or anti-Israel or pro-Israel.
How could you even know what other people would equate with what?
