Security Vulnerabilities in AI-Generated Code | Blog | Endor Labs ※2 [2508.21634] Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity
Review in the Age of AI: A Vision for Agentic Code Review ※2 [2510.10165] AI-Assisted Programming Decreases the Productivity of Experienced Developers by Increasing the Technical Debt and Maintenance Burden
So much for ‘trust but verify’: Nearly half of software developers don’t check AI-generated code – and 38% say it's because it takes longer than reviewing code produced by colleagues | IT Pro