All articles — Page 10
Gemini 3.1 Pro for code-related tasks: more focus, higher signal-to-noise
In practice, developers experience AI code review through the comments it leaves on pull requests: how often it finds real issues, how much noise it produces, and how actionable its feedback is. To an
The one thing devs will still read when they stop reading code
Code was never meant to be read. We just had no alternative. Consider a real-world example: a production payments service with layered retry logic, idempotency keys, circuit breakers, feature flags, a
Faster AI code reviews with NVIDIA Nemotron 3 Super
TL;DR: NVIDIA Nemotron 3 Super delivers high accuracy and faster throughput in CodeRabbit's self-hosted AI code reviews. We are happy to share that CodeRabbit is expanding its support for the NVIDIA N
Introducing usage-based add-on. Allow unrestricted access to CodeRabbit CLI through agentic coding loops.
CodeRabbit now supports unlimited reviews using CLI, helping you to perfect code while running your agentic coding loops with Claude code, Codex and more! Buy credits, use them at your own pace, and g
Pre-merge checks: built-in & custom PR rules automatically enforced
All development teams claim to have pr standards, which often include requirements like: "Ensure docstrings are added," "Reference the associated issue," and "Avoid logging sensitive information." Def
Introducing one of the most requested CodeRabbit features: multi-repo analysis.
If you've ever merged a pull request that passed every check, looked clean in review, and then broke a downstream service ten minutes later…you already know the problem. When your architecture spans m
A semantic history: How the term 'vibe coding' went from a tweet to prod
A year is an eternity in AI time. In February 2025, Andrej Karpathy dropped a tweet-sized cultural marker into the software world: “vibe coding.” The phrase stuck because it captured a visceral shift
AI is burning out the people who keep open source alive
Over the past few months, one refrain has been heard consistently in open source communities: “AI slop.” It shows up in LinkedIn discussions from CEOs who rarely complain publicly. It shows up in Re
CodeRabbit Skills: give your AI agent code review instincts
AI agents can write code, they can refactor code, they can even explain code. But they don’t review code like a senior engineer. They don’t consistently look for subtle bugs. They miss security risks.