GLM 5.2 纯文本模型竟然能设计网站，还打败了 Fable 5？搭配 Browser Use v2 多模态 QA 代理，成本不到 0.75 美元，太会玩了。
GLM 5.2（纯文本模型）在网站设计任务中击败了 Fable 5。团队将 GLM 5.2 与 Browser Use v2 多模态 QA 子代理配对，让代理审查网站、发现 bug、判断美学，再向 GLM 发送修复指令。整个构建加质量保证的成本低于 0.75 美元。展示了纯文本模型通过智能协作在视觉任务上的潜力。
GLM 5.2 just beat Fable 5 at website design. 🌐 The crazy part: GLM is text-only. It can build the...
GLM 5.2 just beat Fable 5 at website design. 🌐 The crazy part: GLM is text-only. It can build the site, but it can’t inspect the result. So we paired it with Browser Use v2 multimodal QA subagents. > Reviews the site and finds bugs > Judges the aesthetics > Sends GLM targeted fixes to iterate on Build + full QA cost less than $0.75. Try it now ↓ Your browser does not support the video tag. 🔗 View on Twitter Design Arena @Designarena x.com/i/article/2067… 🔗 View Quoted Tweet 💬 2 🔄 2 ❤️ 59 👀 3114 📊 12 ⚡