Alibaba open-sourced its internal AI code review tool, Open Code Review (OCR), under Apache-2.0 after two years of use, claiming it served tens of thousands of developers and flagged millions of defec…
AI code review and AI code verification serve different purposes, according to a comparison by Aviator. AI code review reads a diff and comments on potential bugs, style, and security, but cannot veri…
Anthropic's Claude Opus 5, tested by CodeRabbit, produced cleaner actionable comments but caught fewer bugs and generated more noise than the production baseline. In CodeRabbit's benchmarks, Opus 5's …
A small team built Gatekeeper, a single-file AI PR reviewer for Azure DevOps that enforces compliance gates and runs four parallel AI analysis streams. In a benchmark against CodeRabbit, Qodo Merge, a…
CodeRabbit, an AI code review tool, reviewed a 218-file pull request that removed 74,096 lines from the HiddenWars game codebase, catching issues in a Go interface that mixed two systems. The tool reo…
A developer built a custom AI code reviewer using GitHub Actions and the Gemini API, creating a lightweight automation loop that posts inline comments on pull requests. The system triggers on PR event…
A screenshot from a pull request in the Bun repository shows AI reviewers CodeRabbit and Claude review bot interacting with Robobun, highlighting the growing trend of AI systems reviewing code generat…
CodeRabbit launched Post-Merge Actions, a feature that lets its AI agent automatically execute follow-up tasks such as updating changelogs, bumping versions, or creating tickets after a pull request m…
AI coding tools like Claude Code, Cursor, and Codex are generating functional code that often contains security vulnerabilities, according to multiple reports from Veracode, CodeRabbit, and Apiiro. Th…
CodeRabbit introduces Quiet mode, a new review profile that preserves full AI code review depth while reserving inline comments for critical and major findings, after observing that trusted teams no l…
Researchers at the University of Missouri-Kansas City disclosed the Ghostcommit attack, which hides malicious prompt-injection instructions inside a PNG image referenced by an AGENTS.md file to turn A…
ASSET Research Group and Sudipta Chattopadhyay published a proof-of-concept attack called Ghostcommit that hides a prompt-injection instruction inside a PNG image, passes AI code review, and later ind…
Brandon Gubitosa of CodeRabbit reports that 2026 is becoming the year of AI quality, as engineering teams shift from generating code to understanding and trusting AI output. Stack Overflow's 2025 Deve…
Anthropic launched Claude Code, a terminal-first agentic coding tool with Computer Use integration, multi-file edits, persistent shell sessions, Git operations, and fine-tuning support. The tool compe…
Researchers at the University of Missouri-Kansas City developed 'Ghostcommit', an attack that hides prompt injection instructions inside PNG images to trick AI code reviewers into approving malicious …
Researchers at ASSET Research Group published a proof-of-concept attack called GhostCommit that exploits coding-agent pipelines by hiding exfiltration instructions inside image files in pull requests.…
AI hype is being used by companies as a cover to replace stable employment with precarious gig work, according to research and interviews. The trend accelerates gigification as laid-off tech workers t…
The Kubernetes community has introduced a framework for integrating AI into open-source maintainership that prioritizes human accountability, requiring transparent disclosure of AI usage in pull reque…
OpenAI released GPT-5.6 with three tiers—Sol, Terra, and Luna—for coding agents. Sol excels at long-horizon tasks and code review, while Terra offers a cheaper option for scoped work. The release intr…
AI agents differ from chatbots by placing an LLM inside a loop where the model decides when to stop, enabling autonomous task completion. The progression from single LLM calls to function calling, cha…