Anthropic introduces Claude Code Review, so you don't even need to check all of your own AI slop
If you think we left vibe coding behind in 2025, when Collins Dictionary awarded it word of the year, think again, buddy. Not only do you not have to write your own code, but Anthropic's Claude has introduced a code review tool in the research preview that you can do on-site, without extra plugins… buddy. Shown in action on the Claude YouTube page, you can enable 'Code Review' in Claude admin settings, where you can get "a team of agents" to crawl through your codebase and flag any bugs. Once opens, it will "search for bugs in parallel, verify each one to filter out false positives, and rank findings by severity."Claude says this new code review tool is modelled on the one it runs internally at Anthropic. It argues that code reviews are a bottleneck for engineers. The review won't approve any pull requests by itself, "but it closes the gap so reviewers can actually cover what's shipping."The head of AI at Hedgineer, a hedge fund asset management software company, took to X to share their experience with the new Code Review function. They say, "Other than not needing a trigger like a GitHub Action and being configurable directly inside Claude Desktop, I see absolutely NO additional functionality or improvement over just setting up claude.yml with the /install-github-app command."Effectively, they already had an AI code review in process, and claim they see little benefit, other than the convenience of it. Countering this, Claude coder Thariq claims the new code review tool "uses a lot more compute and tends to catch more difficult bugs"
Naturally, using that extra compute can be costly, and reviews are billed on token usage, generally averaging $15-$25, with larger and more complicated pull requests costing more. Anthropic states, "Code Review optimises for depth and may be more expensive than other solutions, like our open source GitHub Action."Ironically, I can see the use of a relatively expensive tool like this providing more value to manual code, assuming it works well. That's because human code will be fairly limited in scope and size, so there's less to comb through. According to a paper from January this year, vibe coding has a measurably poor impact on open source software. It reportedly raises productivity, but "it also weakens the user engagement through which many maintainers earn returns."AI coding tools provide a sizable volume of code, some of which can be good, but review will take longer when paired with productivity gains. This is before mentioning cases of AI coding tools destroying entire databases. Even companies as big as Amazon have seen outages thanks to AI coding tools. Still, as Anthropic clarifies, tools like Code Review are designed to give greater compute to code checks, so we'll have to see it tackle much larger projects to fully understand how effective it is, and if it's worth the price.