AI code reviewers

A music video titled 'LGTM (Looks Good to Me)' built with the Claude Opus 5.5 AI model is circulating widely. Commenters are discussing it as an example of AI-generated creative work, with reactions split between amusement at the code-review joke in the title and debate over the quality and implications of AI-made media.

A scoping review published in Nature used AI assistance to assess how often researchers share the code behind clinical prediction models. The review maps the availability and transparency of code in published studies, a key issue for reproducibility in medical AI. Researchers in the field say such systematic evidence will inform reporting standards and open-science practices in clinical prediction modelling.

A new report argues that AI coding assistants may generate higher volumes of code without delivering more usable software, because human developers still need to review and correct what the tools produce. Critics of AI-driven development are citing the finding as evidence that productivity gains from tools like these are overstated when the full cost of human oversight is counted.

Anthropic has launched OSS Scanner, a free service that provides open-source projects with periodic, AI-driven security scans to help uncover vulnerabilities. Projects must opt in to receive what the company describes as thorough, recurring reviews of their code. The move positions Anthropic alongside other AI firms courting the developer community, though some observers will scrutinise how the scans handle sensitive project data.

Programmers are discussing why AI coding agents fail. The argument gaining traction is that most agent failures are not the agent lying, but verification being handled by the same process that did the work. The proposed fix is to write the falsifier before the task: a checklist for checking agent output, so review is independent rather than self-confirming.