HackerTrans
TopNewTrendsCommentsPastAskShowJobs

itamarcode

no profile record

Submissions

Show HN: Chat with Sonnet/GPT4o directly on pull requests in GitHub

pr-agent-docs.codium.ai
1 points·by itamarcode·2 anni fa·0 comments

Coding agent in the IDE: Generate task plan and get plan-aware code completion

twitter.com
22 points·by itamarcode·2 anni fa·14 comments

[untitled]

1 points·by itamarcode·3 anni fa·0 comments

comments

itamarcode
·11 mesi fa·discuss
Unlike most SWE bench submissions, Qodo Command one uses the product directly.

I think that the next step is getting an official "checked" mark by the SWE bench team
itamarcode
·anno scorso·discuss
AI code review will very probably have signal-to-noise problems. It is good to see practical solutions aimed at addressing this. I wonder if fine-tuning models would help - this isn't addressed in the blog.
itamarcode
·anno scorso·discuss
So protecting models behind API isn't working, ha?
itamarcode
·2 anni fa·discuss
While Sonnet-3.5 excels in accuracy-token, o1 excels in self-reflection in small isolated tasks. With AlphaCodium, o1 tasks are broken to small isolated tasks, while the flow introduced in AlphaCodium actually guides the steps and overall decision making framework.

We will see more of these frameworks for different use cases
itamarcode
·2 anni fa·discuss
Did you get any response from users detecting this automation?
itamarcode
·2 anni fa·discuss
Hey, co-creator here, I agree with the sentiment that code coverage may be a proxy and even sometimes a vanity metric but at the same time, IMO unit regression tests are necessary for a maintainable production codebase. I personally don’t feel confident making changes to production code that isn’t tested.

Specifically for generating unit regression tests the Cover-Agent tool already works quite well in the wild for some projects, especially isolated projects (as opposed to complex enterprise-level code). You can see in the few (somewhat cherry-picked) examples we posted [0] that it generates working tests that increase coverage (they were cherry-picked in the sense that these are examples we like to work with often internally at CodiumAI).

I believe that it’s possible to generate additional meaningful tests including end-to-end tests by creating a more sophisticated flow that uses prompting techniques like reflection on the code and existing tests, and generates the tests iteratively, feeding errors and failures back to the LLM to let it fix them. Just as an example. This is somewhat similar to the approach we used with AlphaCodium [1] which hit 54% on the CodeContests benchmark (DeepMind’s AlphaCode 2 hit 43% [2] with the equivalent amount of LLM calls).

If like me you think tests are important but hate writing them, please consider contributing to the open source to help make it work better for more use cases. https://github.com/Codium-ai/cover-agent

[0] https://www.youtube.com/@Codium-AI/videos [1] https://github.com/Codium-ai/AlphaCodium [2] https://storage.googleapis.com/deepmind-media/AlphaCode2/Alp...
itamarcode
·2 anni fa·discuss
This is interesting. Are there specific use cases for which it works really well?
itamarcode
·2 anni fa·discuss
Hey, one of the creators here. As mentioned in the post, TestGen-LLM (by Meta) focused on Kotlin, and the prompts were very Kotlin-oriented. In Cover-Agent (by CodiumAI) we tried to reimplement Meta's work, and stay mostly similar to the original implementation, although we did a bit improved the prompts. But it isn't generic enough. We believe we know how to improve generality, as we did with our PR-Agent, and here is a rough plan: https://github.com/Codium-ai/cover-agent/issues/13
itamarcode
·2 anni fa·discuss
Can it consider an existing code base? rather be inspired by it or even integrate with it?
itamarcode
·2 anni fa·discuss
The user can choose the relevant context as follows: go to the relevant code part/snippet/files, select, then Ctrl+shift+E, one by one.

In the near future, the agent will suggest these for you, after first indexing your code base
itamarcode
·2 anni fa·discuss
We will support other, I promise
itamarcode
·2 anni fa·discuss
SaaS uses best of bread from OpenAI, whole enterprise get to choose also from our own model for on prem deployment
itamarcode
·2 anni fa·discuss
Well,

To put it simple: Like copilot, it does have an auto-complete and also chat interface. Different than copilot, it focuses on generating a full code task plan, then having the auto completion work acrroding to your plan, and it check the of quality code.

Like agents, it tries to help you complete a full task, yet,does that in tandem with you, as you work inside tour favorite IDE writing the code with you. In addition, there is focus on code quality, testing, and fetching relevant context from your codebase.
itamarcode
·2 anni fa·discuss
Hey HN, CodiumAI co-founder here.

We’ve come up with a bit of a different concept for what a coding agent should be. We believe it should work in tandem with a developer inside the IDE. Over time as the tech improves, it will get more and more autonomy.

We’ve been using our coding agent internally and see a 5-10x boost on some tasks.

The agent is available now to Codiumate VS Code users. We want to hear what kind of tasks it works well on and improve it over time to expand the task set. Would love to get feedback.

https://marketplace.visualstudio.com/items?itemName=Codium.c...
itamarcode
·2 anni fa·discuss
Seeing a good demo, and a credible influencer actually trying the product
itamarcode
·2 anni fa·discuss
Oh, this looks very useful. Do you have a success story?
itamarcode
·2 anni fa·discuss
Hey, this is one of the makers here. Feel free to ask me anything.

Paper: https://arxiv.org/abs/2401.08500 Blog: https://www.codium.ai/blog/alphacodium-state-of-the-art-code...
itamarcode
·2 anni fa·discuss
Paper: https://arxiv.org/abs/2401.08500 Blob: https://www.codium.ai/blog/alphacodium-state-of-the-art-code...
itamarcode
·3 anni fa·discuss
What are the main topics you think you will cover?