⚡Megatron LLM Hub
←Back to search
Twitter

GPT-6 直接改写 Qwen3.5-9B 权重,安全基准升 19 分但误报增三倍

基准分提升不等于能力提升,做 LLM 安全评测时需警惕分数陷阱
llmai_agent报告
RT @pdiscoveryio: We let GPT-6 Astra directly edit Qwen3.5-9B's weights with no fine-tuning or gradient descent. SecEval: 32.5% → 51.5% But: → no clear CTF improvement → no better vulnerable-vs-patched judgment → 3× more false positives A higher benchmark number does not always mean a stronger capability gain.