What your review queue's ranker can and cannot see
A team with more open pull requests than review hours does not need another reviewer first. It needs something that decides which pull request to lo…
Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Все темы
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
testing
tutorial
typescript
webdev
AI code review just delayed PostgreSQL 19. Finding bugs is now cheap and fixing them isn’t.
PostgreSQL 19 was supposed to ship in October. The release team now says general availability is November 19, with RC 2 on November 12 (postgresql.o…
How to review pull requests written by coding agents
A pull request from a coding agent usually looks better than one from a tired human. The description is complete, the code is formatted, the tests p…
Which of your rule files the reviewer actually reads
Every AI review tool claims it reads your AGENTS.md or CLAUDE.md. What decides whether your standards actually land is which rule wins when two appl…
Review debt in the AI era cannot be repaid by reading more
Originally published at https://aicoding-guide.com . Review debt cannot be repaid by reading more. It can only be repaid by shrinking the unit you s…
The artifact worth reviewing when agents write the code
GitHub's Security Lab reported 24 Android vulnerabilities found by an AI security agent, and the part worth copying is what ended up version-control…
Your AI review bot is training you to ignore it
A year ago we turned on an AI reviewer for every PR. Last month we turned most of it off. Not because it was wrong — because it was noisy, and noise…
The Bottleneck Moved: AI Coding Agents Write 30% More Code, but Teams Ship the Same
Most teams that adopted AI coding agents expected one thing: ship faster. A new Harvard working paper on 718 companies suggests they got the opposit…
Your Agent's PR Grows Three 'While I Was in Here' Cleanups, and Now You Can't Review It
You ask your agent to add one endpoint. You come back to a diff that contains: the endpoint you asked for, a renamed variable across fourteen files,…
Claude Code and Linus Torvalds: the Linux patch tradeoffs
Claude Code helped Linus Torvalds explore a Linux memory-management change, write test programs and draft its explanation. The interesting part is i…
30% More Code, Zero More Shipped Work: Where the Capacity Actually Went
A Harvard study of 718 firms found that coding agents produced 30% more lines of code and no detectable increase in finished work. Most coverage sto…
Code Is the New Assembly. Stop Reviewing It.
Code Is the New Assembly. Stop Reviewing It. Gergely Orosz, the voice behind The Pragmatic Engineer with over a million subscribers, recently posted…
Your Agent Renamed the Function — It Just Missed the Caller That Referenced It by String
The rename that looks safe You ask the agent to rename process_payment to settle_payment . It runs across the codebase, updates every import, rename…
Your Agent Writes the PR Description, but It Only Tells You What the Code Does
The description that reads like a code tour You open a PR from your agent. The description is tidy: Added input validation for the /checkout endpoin…
AI review benchmarks score the bot. Nobody scores the reader
This week GitHub published ReviewBench , an open benchmark for AI code reviewers. It is careful work: 219 pull requests from 187 open-source reposit…
Where AI review saves time: the write-back, not the analysis
A tool that "supports Azure DevOps" may only be able to read your pull request. What cuts review time is the write-back: posting an inline comment w…
Code Review: When Checkout Success Still Breaks Inventory
A checkout can return success after reducing stock without creating an order. It can also accept two purchases when only one unit exists. Lab 09 mak…
Open source code review: why Hono restricted outside pull requests
Open source code review has a capacity problem, and Hono has drawn a boundary around its queue. On October 5, creator Yusuke Wada said external cont…
How Hard Should You Review This? Ask What It Touches.
When a pull request shows up and an agent helped write it, the first question a lot of reviewers ask is "did an agent write this?" I get why. We bui…
I made CodeRabbit's reviews a third less noisy with an open-source Claude Code skill
AI code review has a noise problem. On a public benchmark of 50 real pull requests, CodeRabbit raised 300 issues. 77 of them were real bugs on the b…
I let a Claude Code agent handle my PR review comments. Only 1 of 6 bot comments was a real bug.
I work on a large production e-commerce monorepo (13 apps). I set up a Claude Code cloud routine that runs every hour: it reads new review comments…
Optimizing Pull Request Reviews: Balancing Code Volume and Efficiency in AI-Assisted Development
Introduction The rise of AI-assisted development has unleashed a torrent of code, transforming the once-manageable pull request (PR) into a sprawlin…
Your pull request review time is mostly waiting and rework
Time to merge is the number teams quote when they say AI review sped things up. It bundles at least three separate costs, and reading the diff is on…
AI code review that follows your team's rules: what each tool actually ingests
"Follows our coding standards" is the phrase teams use when they mean "does not post the same generic nit for the fourth time." It sounds like one f…
Copilot code review on Azure Repos needs three admins and it's still limited preview
The Azure DevOps buyer question keeps landing in my inbox: what's the best AI code review tool for Azure Repos? Almost every reviewer in this space…
7 Best Code Review Tools for 2026
Code review tools are changing quickly. Traditional static analysis still matters, but development teams now also need help reviewing larger pull re…
Code Review in the Age of AI: Is Manual Review Still Enough?
Introduction Software is being built faster than ever. AI assistants can scaffold a feature in minutes, leading to more pull requests, larger diffs,…
When AI-generated code outruns the reader, the fix is tooling, not a stronger reviewer
Six months before the Miden zkVM audit even started, Trail of Bits had already spent most of the real work. Not staring at code. Building an LSP ser…
Cutting PR review time is an orchestration problem, not a reviewer problem
The usual answer to "how do we reduce PR review time" is to make the reviewer faster. Vendor pages recommend an AI reviewer that reads a diff in sec…
A Benchmark Should Catch the Bug Your Examples Don't Mention
A benchmark that only checks the examples in the prompt is measuring the wrong thing. I ran into this while building a small code-repair evaluation…