Gemini 3.1 Pro for code-related tasks: More focus, higher signal-to-noiseWe evaluated Gemini 3.1 Pro and found it leaves fewer, more focused comments with a higher signal-to-noise ratio, but also surfaces fewer bugs overall6 min read·coderabbit.aiMar 12
Developers are dead? Long live developers.Rumors of developers' death are greatly exaggerated. AI is shifting developers' role from writing code to strategy, reviewing, and defining intent.8 min read·coderabbit.aiFeb 12
Why users shouldn’t choose their own LLM models: Choice is not always goodLetting users pick LLMs hurts quality, consistency, and cost. Learn why model selection is a data-driven engineering problem—not a user preference.7 min read·coderabbit.aiJan 9
An (actually useful) framework for evaluating AI code review toolsA vendor-neutral framework to evaluate AI code review tools using your own PRs, severity labels, metrics (precision/recall), and a real-world pilot.11 min read·coderabbit.aiJan 9
Our new report: AI code creates 1.7x more problemsWe analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.7 min read·coderabbit.aiDec 17, 2025