CodeRabbit says Codex helped it ship 20 times more software
Its CEO estimates GPT-6 Astra caught about half the issues in CodeRabbit's internal review benchmark.
Stories per day · 30 days
7 RSS
Relatedai-coding5codex5openai4anthropic3ai-agents2claude2claude-code2coderabbit2developer-tools2open-source2software-engineering2ai-tools1antigravity1application-security1cicd1cloudflare1coding-agents1daybreak1
25 stories, newest first · one card per story
Stories tagged #code-review
Blog argues unreviewed AI proxy work should be fireable
The author distinguishes guided AI use from pasting agent output with no review, disclosure, or ownership of failures.
Qodo builds context into AI code review with Codex
Qodo launches a plugin for OpenAI's Codex that provides organizational context and codebase standards to help developers catch P0 bugs across repositories.
Engineer argues agent-written code still needs human ownership
A SonarQube complexity flag on Codex-generated React code led the author to inspect, then have the agent split one file into ten.
1
Greptile uses GPT-6 Astra to test apps beyond code review
The startup also wires its knowledge base to Codex over MCP and cites Daybreak for customer defenses.
CodeRabbit uses GPT-6.1 Sol for codebase security review
The model reviews pull requests and wider scans, and can draft fixes that people must approve.
1
Google open-sources Elephant-Goldfish plugin for AI coding reviews
Stateless reviewer sessions must restate the design and hunt gaps before a go/no-go on files and signatures.
Farol offers a pull-request risk map for approvers
The Hacker News post has 42 points and 25 comments, and the feed gives no further product details.
SecPRBench measures agentic security review on real bug-introducing commits
Recall spans 32.5% to 78.1% across eight frontier models on 265 tasks from nine systems, led by Grok 4.6 and GPT-6 sol.
Torvalds backs AI use by competent kernel developers, not drive-bys
Kernel maintainers are dropping the Assisted-by tag, so submitters no longer must disclose AI use.
1
Cloudflare cuts AI code-review cost 68% to $0.77
Median review time fell from 4 minutes 9 seconds to 1 minute 32 seconds after the changes.
5
AI Can Write the Code. Who Verifies It?
A Faros study and tooling survey say AI coding raises bugs and incidents unless automated verification keeps pace.
20
Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
The Claude Code team uses continuous Claude review so humans focus on higher-level code risks.
How the Claude Code team does code review
Anthropic says Claude now reviews most Claude Code changes as pull requests surged and reverts fell.
22
AI-generated changes create review bottlenecks in software delivery
JetBrains finds most DevOps teams run CI/CD, while AI-generated changes slow code reviews.
AI coding agents generate more code, but not more software
A study finds AI coding agents speed coding but raise pull-request review time 49% and change requests.
3
GitHub’s ReviewBench puts AI code reviewers to the test
GitHub launched ReviewBench, a 219-pull-request benchmark for testing AI code-review agents.
3
Writing code by hand is over, forever
An engineer says Claude Opus 4.5 in Claude Code ended his 18-year habit of writing code by hand.
5
Jev Based Code Review
Hacker News discusses egma-ai's Jev code-reviewer repo, with no technical details given.
Code Security Review tool
Karma Pro, an open-source macOS scanner, reviews multi-language code with AST, heuristics, and an ML classifier.
Not In My Git Yard: Catching Backdoors at Commit and Release Time
An arXiv paper proposes catching software supply-chain backdoors during Git commits and release workflows before code ships.
AI is adding to the review load on open-source projects, many of them thinly funded
ACM Technology Policy Council authors warn AI-generated code is overwhelming thinly funded open-source maintainers, raising software supply chain security risks.
3
GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?
Entelligence benchmarks GPT-5.6 Luna ($1.20/M output) against GPT-6 Astra for code review: Luna found 69 verified bugs at 3.6% of Astra's cost.
1
Cognition helps Devin test its own work with GPT‑6 Astra
Cognition integrates GPT-6 Astra into Devin, its CLI, and desktop products to automate testing and provide evidence for code review.