AI code reviewers

A question on Hacker News asks whether developers are actually producing good code with coding agents like AI assistants that write code autonomously. The poster, ruffrey, wants concrete examples of success rather than hype. The discussion, which drew modest engagement, touches a live nerve in software engineering as teams weigh productivity gains against quality and review overhead from AI-generated code.

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.

Engineer Alexey Indeev has written that he no longer reviews code produced by his AI agents, and describes the alternative workflow he uses instead in a Substack essay. The piece has drawn modest attention on Hacker News, where developers are weighing whether traditional code review still makes sense as more work is delegated to autonomous coding agents.

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.

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.

An engineer has shared five lessons from running Anthropic's Claude Code as a cloud agent every hour on a large production monorepo. The write-up covers validating review comments, preventing the agent from getting stuck in loops, fixing a 403 error, and reducing token consumption. The post is drawing attention from developers interested in using AI coding agents for automated code review in real production environments.

The open-source firmware project Coreboot has released version 26.09, adding support for the Framework Laptop 12 and introducing a new policy on AI-generated comments in code reviews. The release matters to users who want open firmware alternatives to vendor BIOS on recent hardware, particularly the modular laptop maker's latest device.

A new kind of coding challenge is making the rounds: instead of writing code, developers are asked to review a pull request containing three deliberately planted bugs and find them. The exercise inverts the usual interview format, testing code review and reading skills rather than implementation. Programmers are debating it as a fairer, more realistic test of everyday engineering ability.

A software engineer writing on Substack says he no longer manually reviews the code produced by his AI coding agents, and has adopted a different approach instead. The piece is drawing attention among developers debating how much oversight AI-generated code needs, as teams increasingly rely on agents to ship production changes with limited human inspection.

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.

SpaceX has reportedly completed a $60 billion acquisition of Cursor, the AI coding company, in what would fold enterprise AI software into a business better known for rockets and Starlink satellite internet. Reports frame the deal as adding a new AI revenue stream alongside Starlink's connectivity business. Details on regulatory review and how Cursor fits into SpaceX's structure remain limited, so the full scope of the deal is still unclear.

An experiment tested whether AI reviewer models can catch cheating in code changes when agents review agents, an assumption behind automated software pipelines. Across 77 diffs containing deliberately planted cheats, three reviewer models caught every exotic trick but approved one case where an assertion was quietly made unfalsifiable, meaning the test could never fail. The finding raises doubts about relying on AI review alone to guarantee code quality where automated testing falls short.

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.

Software testers are discussing a workflow where an AI agent runs plain-language test cases in a headless browser, using self-healing to keep scripts working as applications change, while only scenarios worth keeping long-term get promoted into maintained code. Supporters say it cuts maintenance burden on QA teams; others caution that AI-run tests still need human review before being trusted in release pipelines.

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.

MIT and Sakana AI have introduced a new framework that uses a large language model as an automated judge to evaluate the output of self-improving coding agents. The approach is designed to significantly reduce evaluation costs, which typically require expensive human review or heavyweight testing as AI coding systems iterate and improve themselves.

A new article argues that over-reliance on AI assistance can quietly lower software quality, as teams stretch their review capacity and miss hidden edge cases in generated code. It offers practical habits for developers to counter this, from deliberate code review practices to stronger team routines around testing and quality control.

A Communications of the ACM opinion piece argues that AI coding assistants have not made software development easier, but shifted where the difficulty lies. Rather than eliminating hard work, developers now face new challenges around reviewing generated code, understanding systems they did not write, and verifying correctness. The argument is resonating with programmers debating whether AI tools genuinely boost productivity or simply replace one kind of effort with another.

A university instructor says that this term they replaced their own live coding in review sessions with Claude Code, an AI agent, doing the typing while the class read what it ran and judged the results. They describe experiments with different modes: plan mode produced a giant wall of text after three or four cycles on a simple task, while auto mode got the task right. The approach is drawing attention as a teaching experiment.

A new opinion piece in Communications of the ACM argues that AI coding assistants have not made programming easier, but have shifted where the difficulty lies. The author contends developers now face different challenges, such as reviewing, verifying and directing machine-generated code, rather than writing everything themselves. The argument is circulating among developers and prompting debate about whether AI genuinely boosts productivity in software work.