AI code review tools

OpenAI has made its automatic code review feature free for all Codex users. The tool reviews code changes automatically, giving developers feedback without a paid tier. The move is being discussed as a way to pull more developers into OpenAI's coding ecosystem at a time when automated code review and AI coding assistants are a highly competitive market.

A developer has published a first-hand review of OpenAI's new Codex desktop application, concluding that the user interface is the real product rather than the underlying coding model. The write-up walks through the reviewer's initial experience using the app and argues OpenAI is putting significant weight on design and workflow. It lands amid heavy developer interest in AI coding tools and OpenAI's expanding product line.

IBM's AI-powered vulnerability clearinghouse has identified hundreds of security flaws in Java software. The finding highlights the growing role of artificial intelligence in scanning open-source code for vulnerabilities at scale, giving developers advance warning of weaknesses that attackers could exploit. Security teams are expected to review the affected Java components.

System76, the company behind the Pop!_OS Linux distribution, has banned AI-generated code across many of its COSMIC codebases, the desktop environment underpinning the operating system. The decision bars contributions written by AI tools from large parts of the project, with developers expected to write and review code themselves. The move is drawing attention and debate among open-source developers weighing code quality, licensing and trust issues around AI-assisted programming.

GitHub has introduced ReviewBench, an open benchmark for measuring how well AI models perform code review. The benchmark is intended to give developers and researchers a standard, reproducible way to compare the quality of AI-generated code review feedback, as AI assistants are increasingly used in real software development workflows.

A new project called oh-my-agent has been presented on the German Ubuntu users forum, describing how existing code agents can be used to carry out automated project reviews. The thread, published under the Linux and open source sections, explains how developers can apply the tooling to check their current codebases. Responses so far appear limited, with the discussion still in an early stage.

Former OpenAI researcher Andrej Karpathy argued on X that as AI writes more of the code, the programmer's job shifts from typing to reviewing and supervising the machine's output. The remark is circulating among developers, many of whom see it as a fair description of how AI coding tools are already changing day-to-day software engineering and what skills will matter next.

OpenAI's Codex, the company's AI coding agent built on its GPT models, is generating renewed discussion as developers and tech commentators weigh it against ChatGPT. The conversation centres on how the two tools fit together: ChatGPT as the general assistant and Codex as a specialised tool for writing and reviewing code inside developers' workflows.

Heise is hosting a live webinar on developing, deploying and reviewing software with AI coding agents in Xcode. The session covers Claude Code, GitHub Copilot and OpenAI Codex, with a focus on using the tools without compromising security or data privacy. The announcement is circulating among developers interested in AI-assisted programming workflows.

A developer is offering a paid human second-pass review of AI-generated pull requests, and says they reviewed three AI-written PRs from public repositories before pitching the service, which they call Riven Desk. The idea taps into growing concern that AI-written code is being merged without careful human scrutiny. Commenters in programming and engineering communities appear engaged with the question of how much review AI code actually needs.

A newly shared engineering write-up describes building an edge-agentic commit analyzer, a tool that reviews code commits locally using AI agents running on local hardware rather than cloud services. The piece focuses on troubleshooting stubborn errors that arise in local environments. Reaction so far is limited, but the topic touches on ongoing developer interest in running AI coding tools offline for privacy and cost reasons.

A developer has published findings that CodeRabbit, a popular AI-powered code review tool, produces excessive noise when reviewing real pull requests. On a public benchmark of 50 genuine pull requests, the tool flagged far more issues than necessary, and a modification reduced its review noise by roughly a third. The work has sparked discussion among developers about whether AI review tools create too many low-value comments that slow teams down.

Discussion is growing around whether open source software projects can keep pace with AI tools that generate code far faster than human developers. The concern centres on how volunteer-driven communities, which maintain much of the world's critical software infrastructure, will absorb or compete with automated code production while still ensuring quality, security and proper review.

A new blog post by Andrew Moffat argues that changes generated by AI should be evaluated and designed to minimize the cognitive load they place on developers reviewing them. The piece discusses how programmers can structure AI-assisted modifications so they are easier to understand and verify. It is being shared among software developers discussing the practical challenges of integrating AI tools into everyday coding workflows.

Former Google CEO Eric Schmidt said the best programmers no longer write code themselves, pointing to a shift toward directing AI tools that do the coding instead. His comments highlight how artificial intelligence is reshaping software engineering, with experienced developers increasingly acting as reviewers and architects of machine-generated code rather than typing it out line by line.

A common workflow flaw is drawing attention: when a reviewer approves a change, an AI coding agent can make further edits while the task still displays as approved. The problem arises because approval is attached to the task rather than to a specific delivery. Commenters argue a solid review process should clearly define what was approved, at which point, and whether later edits require re-review.