Pull Request Reviewed by LLM
This year I’ve reviewed more than 1000 code changes. Most of the time was spent catching obvious mistakes rather than debating complex design decisions. If we estimate ~10 minutes per review, that’s 160+ hours spent reviewing code in just one year. So I thought: could I get some of that time back using LLMs? That's why I spent the last few weekends building an LLM-based prereviewer that should take a first pass before the actual human reviewer. The results so far are promising: I estimate it can reduce the review time by 50%, which in my case would mean I save 80hours (~10 working days) per…
Pull Request Reviewed by LLM launched on November 22, 2024 with 9 votes, #2,254 of 4,990 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Contribute to presubmit/ebank-backend development by creating an account on GitHub.
Co-authored-by: aipresubmit[bot] <183662906+aipresubmit[bot]@users.noreply.github.com> indentation 6568d21 Merge branch 'main' of https://github.com/presubmit/ebank-backend int… … d0f3995 …o test github-actions Bot commented Nov 22, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page . Extended the access token validity period from 20 minutes to 20 hours and fixed a critical bug in refresh token validation logic. The refresh token validity remains unchanged at 2 hours. Also made token validity variables public by capitalizing their names. The reason will be displayed to describe this comment to others. Learn more . Co-authored-by:…from github.com
In the maker’s words, at launch
This year I’ve reviewed more than 1000 code changes. Most of the time was spent catching obvious mistakes rather than debating complex design decisions. If we estimate ~10 minutes per review, that’s 160+ hours spent reviewing code in just one year. So I thought: could I get some of that time back using LLMs? That's…
Does a similar job
all alternatives →
Open-Source Pull Request AI Reviewer2024 · github.com · ▲5Hey HN, Over the last year, I’ve reviewed more than 1000 code changes. Most of the time was spent catching obvious mistakes rather than debating complex design decisions. If we estimate ~10 minutes per review, that’s 160+ hours spent reviewing code in just one year. So I thought: could I get some of that time back using LLMs? That's why I spent the last few weekends building Presubmit.ai, an open-source AI reviewer that runs as a Github Action right when you open a Pull Request. The results so far are promising: I estimate it can reduce the review time by 50%, which in my case would mean I…
Why write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Guide to better pull requests and code review2023 · github.com · ▲49I listed all the advice I give about Pull Requests and Code Review into a short (37 pages) and free guide, with real-life examples and actionable insights.
- CRCode reviews intimidated me, so I built a course on how to master them2022 · ▲13
I’m excited to share Master the Code Review: forge a better process, give better reviews, write better code. It’s a video course with 4+ hours of content [1]. I’ve linked a 21-minute sample below [2]. 6 years ago, I began my software engineering career at Amazon Web Services. I struggled with Pull Requests. My authored PRs received many comments, sometimes 50+. They went through many revisions, sometimes 7+. I often shipped late. My reviews of other PRs were surface level and counterproductive. Long story short: I improved. Through trial, error and experience I learned how to be effective in…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, November 2024
the whole month →
Lovable▲1,477Hey HN! Previous CERN physicist turned hacker here. We've developed a way to make AI coding actually work by systematically identifying and fixing places where LLMs typically fail in full-stack development. Today we're launching as Lovable (previously gptengineer.app) since it's such a big change. The problem? AI writing code typically make small mistakes and then get stuck. Those who tried know the frustration. We fixed most of this by mapping out where LLMs fail in full-stack dev and engineering around those pitfalls with prompt chains. Thanks to this, in all comparisons I found with: v0,…
AI · 2024 · lovable.dev
Postiz▲1,188Streamline your social media with Postiz. Schedule posts, analyze performance, and manage all accounts in one place.
Dev tools · 2024 · postiz.com
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
Raycast Notes▲1,058Unlock a new level productivity with AI, Cloud Sync and more
Work · 2024 · raycast.com
