CodeRabbit Blog
coderabbit.ai · Company blog · on HN since 2023
Company blog of CodeRabbit, an AI code review tool, covering AI-assisted review, benchmarks, and the engineering behind the product.
What HN saysCommenters who use it recommend it for pull request reviews, saying it finds many issues and sees files beyond the diff.
31HN people shared it
15linked it in comments
59stories submitted
359story points
3 months agolast shared
2023people per year2026
Most-shared posts
- 1Show HN: CodeRabbit:AI-Powered Tool Streamlining Code Reviews8 people · 13 points · first shared 2023 · 3 comments on HN
- 2AI helps ship faster but it produces 1.7× more bugs3 people · 206 points · first shared 2025 · 167 comments on HN
- 3Our response to the january 2025 kudelski security vulnerability disclosure action and continuous improvement3 people · first shared 2025
- 4Benchmarking GPT-52 people · 10 points · first shared 2025 · 1 comments on HN
- 5Show HN: AI and the Future of Code Reviews2 people · 7 points · first shared 2023 · discussion on HN
- 6Managing OpenAI Rate Limits with Request Prioritization2 people · 4 points · first shared 2023 · discussion on HN
- 7Using AI to catch S3 config issues2 people · 3 points · first shared 2024 · 1 comments on HN
- 8Code Review Anti-Patterns You Can Eliminate with AI2 people · 2 points · first shared 2024 · 1 comments on HN
- 9The cost of AI coding agents isn't from AI at all2 people · 2 points · first shared 2026 · discussion on HN
- 10CodeRabbit tops the F1 score in Martian's code review benchmarks2 people · 2 points · first shared 2026 · discussion on HN
- 11It's harder to read code than to write it1 people · 25 points · first shared 2025 · 3 comments on HN
- 12Code Quality at Scale with AST Grep and LLMs1 people · 19 points · first shared 2024 · 4 comments on HN
- 13CodeRabbit's AI Code Reviews Now in Your CLI1 people · 8 points · first shared 2025 · 3 comments on HN
- 14Tips for Using GitHub Copilot1 people · 6 points · first shared 2025 · discussion on HN
- 15Why software developers hate linters?1 people · 6 points · first shared 2025 · 3 comments on HN
What HN people wrote when they linked it
bebop · 2025-11-22
We used https://www.coderabbit.ai/ at my work to do reviews and I was a pretty impressed with it. Might be worth a look. Not affiliated in any way.
gillh · 2023-12-10
Interesting use-case: We recently started using ast-grep at CodeRabbit[0] to review pull request changes with AI.
We use gpt-4 to generate ast-grep patterns to deep-dive and verify pull-request integrity. We just rolled this feature out 3 days back and are getting excellent results!
Comments such as these are powered by AI-generate ast-grep queries: https://github.com/amorphie/contract/pull/100#discussion_r1420655994
[0]: https://coderabbit.ai
jcubic · 2026-06-19
I mostly use CodeRabbit via GitHub PR
https://www.coderabbit.ai/
atestu · 2026-06-05
We've been using Coderabbit, great deal ($30/mo/dev flat) and finds a lot.
I also built a skill I call `/meta-review` that asks Codex, Cursor, and Gemini to review the code (I use Claude Code). It always finds little things claude & I missed.
Coderabbit just came out with their own PR review UI that's great for big PRs, it groups files together etc. https://www.coderabbit.ai/blog/introducing-atlas-the-first-ai-native-c…
howToTestFE · 2025-12-21
while this approach is useful, i think the diff is too small to catch a lot of bugs.
i use https://www.coderabbit.ai/ and it tends to be aware of files that aren't in the diff, and definitely can see the rest of the file your are editing (not just the lines in the diff)
philmo1 · 2023-11-15
How does Watermelon compare to CodeRabbit (https://coderabbit.ai)? Very curious!
al2o3cr · 2023-07-14
At the time of writing, the first sample image on that page is this:
https://coderabbit.ai/assets/section-1-f9a48066.png
which recommends adding a "maxIterations" counter to the "for len(executedComponents) ..." loop here:
https://github.com/fluxninja/aperture/blob/26e00ea818c7c28dac00c1a5e1a…
HOWEVER
- the review has failed to notice the logic using "numExecutedBefore" (around line 377) that already prevents the specific bug it is suggesting a fix for
- the suggested change decrements "maxIterations" inside the "for ... range circuit.components
{" loop which means it isn't counting iterations, it's counting components
This kind of suggestion is particularly nasty because it's unlikely that the test suite populates enough components to hit "maxIterations" - so an inattentive reader could accept it, get a green build, and then deploy a production bug!
smb06 · 2026-07-27
I do believe they were trying to use CodeRabbit to review their re-written code.
https://www.coderabbit.ai/blog/ai-can-migrate-your-entire-codebase-rev…
multisport · 2026-02-13
Genuinely one of the most shocking incident reports I have read in a long time, rivals https://www.coderabbit.ai/blog/our-response-to-the-january-2025-kudels…
Ianjit · 2026-01-09
Sorry for the late response!
My guess is they didn't publish it because they only measured it at one company, if they had the data across the cohort they would have published.
The general result that review/re-wrok can cancel out the productivity gains is supported by other studies
AI generated code is 1.7x more buggy vs human generated code:
https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-re…
Individual dev productivity gains are offset by peers having to review the verbose (and buggy) AI code:
https://www.faros.ai/blog/ai-software-engineering
On agentic being the saviour for productivity, Meta measured a 6-12% productivity boost from agents programming:
https://www.youtube.com/watch?v=1OzxYK2-qsI&si=ABTk-2RZM-leTxtR
"But it's different now" :)
intended · 2026-01-09
> https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-stud…
Shows that devs overestimate the impact of LLMs on their productivity. They believe they get faster when they take more time.
Since Anthropic, GitHub are fair game here’s one from Code Rabbit - https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-re…
simonw · 2025-09-20
> Where are the "code-review" agents at?
OpenAI's Codex Cloud just added a new feature for code review, and their new GPT-5-Codex model has been specifically trained for code review: https://openai.com/index/introducing-upgrades-to-codex/
Gemini and Claude both have code review features that work via GitHub Actions: https://developers.google.com/gemini-code-assist/docs/review-github-co… and https://docs.claude.com/en/docs/claude-code/github-actions
GitHub have their own version of this pattern too: https://github.blog/changelog/2025-04-04-copilot-code-review-now-gener…
There are also a whole lot of dedicated code review startups like https://coderabbit.ai/ and https://www.greptile.com/ and https://www.qodo.ai/products/qodo-merge/
codeman001 · 2025-08-21
I use CodeRabbit that helps, but it does not fix the two root issues. I run their free VS code plugin to review local commits first, which catches nits, generates summaries, and keeps me in my editor. The PR bot then adds structure so humans focus on design and invariants. Review state still lives in the forge, not in Git, and interdiffs still depend on history. If Git gets a stable Change-Id, storing review metadata in Git becomes realistic. Until then this is a pragmatic upgrade that reduces friction without changing the fundamental.
https://www.coderabbit.ai/ide
SCdF · 2025-08-20
https://www.coderabbit.ai/blog/our-response-to-the-january-2025-kudels…
> No customer data was accessed
As far as I can tell this is a lie.
The real answer is that they have absolutely no clue if customer data was accessed, and no way to tell. I'm not even sure Github could tell, but it's not clear if the exploits way of generating private keys to access private repositories is any different to what CodeRabbit does in normal operation.