Top all-time · #3794
Greptile
Company blog · greptile.com/blog · on HN as dakshguptaaiprogramming
Greptile is the company blog at greptile.com, writing about ai and programming. Since 2024, 20 different Hacker News readers have linked it 48 times, most often “How we made our AI code review bot stop leaving nitpicky comments”. No feed was found, so read it on the site itself.
Too few sampled comments (11) to say how often HN recommends it.?
Why HN links it
HN commenters mostly link Greptile as an AI tool for codebase questions and code review, along with its pricing and benchmarks pages. One commenter singles out its shipping-faster blog post as a good read.
Summarised by Claude from a sample of 11 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
AI Code Reviews that understand your entire codebase. Automate PR reviews, catch bugs faster, improve code quality with AI-driven analysis. Try Greptile free!
Most-linked posts?
- /5 people · 5 mentions · first linked 2024-11-14
- How we made our AI code review bot stop leaving nitpicky comments3 people · 4 mentions · first linked 2024-12-18
- The Economics of Being a Founding Engineer2 people · 3 mentions · first linked 2025-02-12
- AI code review: Should the author be the reviewer?2 people · 2 mentions · first linked 2025-05-01
- /pricing2 people · 2 mentions · first linked 2024-03-05
- I asked 100 devs why they aren't shipping faster. Here's what I learned2 people · 2 mentions · first linked 2024-04-11
- Models are worse at reviewing their own code2 people · 2 mentions · first linked 2026-07-21
What Hacker News says?
Greptile ( https://www.greptile.com/ ) tries to do that, at least for bug tickets. I recall being annoyed by its suggestions (posted as Linear comments).
Comment linking /
on “Claude Integrations”Submitted How we made our AI code review bot stop leaving nitpicky comments as a story · 257 points
HN discussionYou can also look into https://www.greptile.com/ to ask codebase questions. There's so many AI coding tools out there now. I've heard good things about https://codebuddy.ca/ as well (for IntelliJ) and https://www.continue.dev/ (also for IntelliJ). >The first one "just doesn't work" Haha. You're on a roll.
Comment linking /
on “AI makes tech debt more expensive”Submitted Splitting engineering teams into defense and offense as a story · 212 points
HN discussionWhen I first came across the idea of vibe coding, my first reaction was that this was taking things too far. Isn't it enough that your LLM can help you do - autocomplete - suggest possible solutions to a problem you've taken the time to understand - helps you spend less time reading documentation and instead help guide your approach and sometimes even helps you identify obscure apis that could help you get shit done…
Comment linking /blog/ai-code-reviews-conflict
on “I'm dialing back my LLM usage”Submitted AI code review: Should the author be the reviewer? as a story · 136 points
HN discussionGreptile | Software Engineer | ONSITE San Francisco (SF) | https://greptile.com Greptile is working on AI agents that catch bugs and enforce standards in pull requests. Reviewing nearly 1B lines of code a month for 1000+ companies including Brex, Substack, Whoop, as well as multiple F100s. <20 people, raised ~$30M from Benchmark, YC, Paul Graham, SV Angel and others. To apply, email daksh [at] greptile.com with subj…
Comment linking /
on “Ask HN: Who is hiring? (November 2025)”Submitted The State of AI Coding Report 2025 as a story · 132 points
HN discussionGreptile | Software Engineer (junior, senior, staff)| San Francisco ONSITE | https://greptile.com Greptile is building AI agents that catch bugs in pull requests. Over 2,000 teams including Brex, Whoop, and Substack use Greptile to review nearly 1B lines of code every month. We're a team of ~20 in San Francisco, working on things like better agent evals and sandbox execution environments. We've raised $30M to date,…
Comment linking /
on “Ask HN: Who is hiring? (December 2025)”Submitted Sandboxing AI agents at the kernel level as a story · 89 points
HN discussionRelated: https://greptile.com/pricing
Comment linking /pricing
on “Launch HN: Greptile (YC W24) - RAG on codebases that actually works”Submitted Searching a Codebase in English as a story · 56 points
HN discussionLove this idea and am just signed up. Thanks for the promo code! Also, I really like your blog post about shipping faster: https://greptile.com/blog/ship-faster . Shipping code is so fun that we should all be looking for ways to do more of it.
Comment linking /blog/ship-faster
on “Launch HN: Greptile (YC W24) - RAG on codebases that actually works”Submitted Why Greptile just does code reviews and doesn't also generate code as a story · 54 points
HN discussion> 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... and https://docs.claude.com/en/docs/c…
Comment linking /
on “If you are good at code review, you will be good at using AI agents”Submitted I asked 100 devs why they aren't shipping faster. Here's what I learned as a story · 48 points
HN discussionyou know everything is made up right? And yet it just works. I too use a confidence score in an bug finder app, Github seems to use them in copilot reviews, people will use them until it is shown not to work anymore. on the other hand this post https://www.greptile.com/blog/make-llms-shut-up says that it didn't work in their case: > Sadly, this also failed. The LLMs judgment of its own output was nearly random. This…
Comment linking /blog/make-llms-shut-up
on “Learnings from building AI agents”Submitted DeepSeek R1 is far better than OpenAI o1 at finding bugs in pull requests as a story · 43 points
HN discussionhttps://www.greptile.com/ This works well, however it literally will need to digest an entire repository. So for example if I feed it a repository for a haxe framework, it'll work much better than something like Chat GPT.
Comment linking /
on “Kilo Code: Speedrunning open source coding AI”Submitted How to make LLMs shut up as a story · 21 points
HN discussionhttps://greptile.com/pricing
Comment linking /pricing
on “I asked 100 devs they aren't shipping faster. Here's what I learned”Submitted Ask questions about Git repositories from a web UI as a story · 19 points
HN discussionI use opus for coding and codex for views. I trigger the reviews in each work task with a review skill that calls out to codex[0] I don't need anything more complicated than that and it works fine - also run greptile[1] on PR's [0] https://github.com/nc9/skills/tree/main/review [1] https://www.greptile.com/
Comment linking /
on “Claude Code Agent Teams”Submitted I asked 100 devs they aren't shipping faster. Here's what I learned as a story · 17 points
HN discussionThe signal-to-noise ratio problem is unexpectedly difficult. We wrote about our approach to it some time ago here - https://www.greptile.com/blog/make-llms-shut-up Much has changed on our approach since then, so we'll probably write a a new blog post. The tl;dr of what makes it hard is - different people have different ideas of what a nitpick is - it's not a spectrum, the differences are qualitative - LLMs are reluc…
Comment linking /blog/make-llms-shut-up
on “There Is an AI Code Review Bubble”Submitted Getting LLMs to Generate Funny Memes Is Unexpectedly Hard as a story · 13 points
HN discussionThanks! We go over that on many other pages. Here are some: https://www.greptile.com/benchmarks https://www.greptile.com/greptile-vs-coderabbit https://www.greptile.com/greptile-vs-bugbot
Comment linking /greptile-vs-bugbot
on “There Is an AI Code Review Bubble”Submitted The secret channel that carried 40 years of text messages as a story · 5 points
HN discussionhttps://codereview.withmartian.com/ https://www.greptile.com/benchmarks
Comment linking /benchmarks
on “Show HN: adamsreview – better multi-agent PR reviews for Claude Code”Submitted Greptile Bug Wiki as a story · 4 points
HN discussion
