A study accepted at IEEE ISTAS 2025 found a 37.6% rise in critical vulnerabilities after five rounds of AI self-improvement, highlighting the need for human review of AI-generated code. Best practices…
GitHub's reliability is declining under the strain of AI-generated code, with outages, missing PRs, and a merge-queue bug that silently deleted commits, according to an analysis in The Hangar communit…
AI code review and AI code verification serve different purposes, according to a comparison by Aviator. AI code review reads a diff and comments on potential bugs, style, and security, but cannot veri…
A new report from Faros, based on data from 22,000 developers, shows code churn up 861%, incidents per pull request up 243%, review time up 441%, and 31% more PRs merged without review, signaling the …
Aviator Verify, a new tool from Aviator, checks code against predefined acceptance criteria using semantic analysis and runtime previews, moving human review from reading diffs to approving intent bef…
Aviator's Verify tool introduces an anti-slop registry that uses invariants to automatically catch AI-generated code violating team engineering standards before merge, addressing the gap left by linte…
AI coding tools have made code review the bottleneck, with teams merging 98% more pull requests while review times climb 91%, according to Faros AI. Microsoft research analyzing 1.5 million review com…