Same Flaw, Opposite Verdict: AI Agents Can't Agree What Counts as a Security Vulnerability
中文摘要
AI智能体对安全漏洞认定不一，相同缺陷有时修复，有时视为设计使然。
English Summary
AI agents lack consensus on security vulnerabilities, inconsistently treating identical flaws as either fixable bugs or intentional designs.
Original Excerpt
I found three ways past an AI agent's safety gate. One was quietly fixed, two were closed as "by design" — yet the same bug class is a… Continue reading on Medium »