AI code review tools

A Hacker News discussion asks whether anyone is actually producing good code with AI coding agents, drawing engagement from developers weighing in on their real-world experience with tools like code-generating assistants. The thread taps into ongoing debate over whether AI-written code is reliable enough for production use or still requires heavy human review.

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.

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.

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.