gpt-6POST
实测对比 Opus 5.5 与 GPT-6 Sol 在代码审计上的表现
作者在已审计出多个严重漏洞的代码库上跑两个模型，结论是评测框架比模型本身更关键。
OxElliot 🦀 💀
@elliot_16982026.09.27收录原推发布于 2026.09.26
OxElliot 🦀 💀 @elliot_1698原推发布于 2026.09.26
1/5 The harness matters more than the model. I tested Opus 5.5 @AnthropicAI and GPT-6 Sol @OpenAI on a codebase I'd already audited and found multiple crits. The results matched what I'd seen with older models from both companies.👇🧵
x.com/elliot_1698/status/2103771511039627636采集于 2026.09.27 09:53