The next step for Code Review GPT #338
Replies: 2 comments 1 reply
-
|
Hi Matt .. appreciate all the effort you have put into this project so far but most importantly your maturity in accepting the challenges you foresee and your vision. I stumbled upon this space quite late ( i tried like crazy googling projects in this space and couldn't find anything ..tells you a lot about google search results ) i have been hacking away at a project that has a decent overlap with what you have built so far but is more in line with your vision for this project. It would be great if you could go through this https://takingstock.github.io/codesapper.ai/ .. i have tried to elucidate, as clearly as possible, my views and visions for something comprehensive in this space if you think there is a good intersection of the venn's i would be more than happy to join you on this journey and contribute ( for free , of course ) .. even i love building stuff ..period the main reason i would rather jump on to this project is for a very practical reason .. you already have created something that has decent acceptance and velocity and more importantly i am looking for people that are willing to commit to building something useful ( sadly, my network is full of people that are happily settled in life .. no shade at them but thats the main reason i am throwing this hail mary pass ..lol ) |
Beta Was this translation helpful? Give feedback.
-
|
Hey thanks for your message. Definitely a bunch of overlap between our interests. Your project seems very similar to some rnd work I was doing here. Very happy if you want to take some leadership on the code mapping generation epic. My current focus is on the easy finetuning and running llms in github actions very efficiently. We could make a rather good team here. Feel free to send me an email and we can chat more. Best, |
Beta Was this translation helpful? Give feedback.
-
|
sent :)
…On Tue, Sep 3, 2024 at 2:50 PM Matt ***@***.***> wrote:
@takingstock <https://github.com/takingstock>
Hey thanks for your message. Definitely a bunch of overlap between our
interests. Your project seems very similar to some rnd work I was doing
here
<https://github.com/mattzcarey/code-review-gpt/pull/341/files#diff-3f65de6dc6a7ead38324d77dcc830e4e107d189027af2e2cd37c5d4afc7f2410>
.
Very happy if you want to take some leadership on the code mapping
generation epic. My current focus is on the easy finetuning and running
llms in github actions very efficiently. We could make a rather good team
here. Feel free to send me an email ***@***.***> and we can chat
more.
Best,
Matt
—
Reply to this email directly, view it on GitHub
<#338 (reply in thread)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AD3M73BLIZYYUZTJTDAKNKLZUV5MFAVCNFSM6AAAAABKTC452SVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTANJSHE3DQNI>
.
You are receiving this because you were mentioned.Message ID:
***@***.***
com>
|
Beta Was this translation helpful? Give feedback.
-
Hey everyone,
Thanks for all your interest and support of this package. Lots of changes have been happening in my life in the last 6 months hence the stall in progress. I wanted to share some updates on Code Review GPT and my thoughts about code review tools more widely.
Looking at the current state of market of these AI-powered review tools as of July 2024, Code Review GPT is up against increasingly sophisticated alternatives such as CodeRabbit and Codium. These companies are raising huge amounts of money to automate away the review process. The question is to me, whether this is sustainable or the right time to be doing this. Obviously raising money for this is not something that I am not going to do.
I believe there is another way to make a great tool especially in the code review space. Looking back over the last year I see that the majority of the gain in this field has not been from the advances in code understanding but by the increasingly performant agentic abilities of AI models such as Sonnet 3.5, and to some extent GPT 4o. This is not an advancement rate which more money or team members in these previously mentioned companies can alter.
I think there is a space for a more open method which piggybacks off these model advances and those of researchers in the space more than it does to create its own IP. An easily configurable, and flexible platform for code review and understanding, using primarily state-of-the-art foundational models but leaving the door open for locally fine-tuned LLMs. If this package provides the ability to use local models then it should also provide a method to build them easily. That is where I believe that this niche will lead and I want to bet on it.
Last summer I derailed this project trying to build out a SaaS tool. We decided to go with a Serverless specific hosting solution of a GitHub app. This was designed to be able to be easily deployed by us and used by you for some nominal fee. In this new phase I want to take this back to basics. I think we can get a huge amount done as a GitHub action and this will be more approachable to more people. We will not tie ourselves into another hosting provider. I will be building the package code into a container for deployment as an app if necessary but this will be secondary to the main package. This project should be about building the best open project not trying to make a quick buck.
For the short term I have some UX improvements on my mind for CRGPT. These are in no particular order
Things I will not work on but will be very happy for others to:
Future upgrades:
If anyone is looking for some open source LLM hobby contributions or maintainer roles please pop me a message. This new phase is going to need more than just me. You will be working for free (at least in the beginning), will need an interest in the space and preferably another job. If that sounds interesting let me know.
I have learnt a huge amount in this last year about code understanding and I am looking forward to build that back into this project.
Have a great week,
Matt
Beta Was this translation helpful? Give feedback.
All reactions