Tencent Hy(@TencentHunyuan):The AI says the site is done. Then the homepage errors, the buttons overlap, and it added a login flow you never asked for. 🙃 Introduces WebCraftBench: agents actually use the live app, coverage-guided exploration finds what never got reached, then we score aesthetics, usability, and whether the original request was met. On 197 human-validated pairs, it matches human preference 85.3% of the time. Paper:

Tencent Hy

@TencentHunyuan

Tencent's foundation model for text, image, video, and 3D generation.

가입 July 2024

8 팔로잉 중 53K 팬

Tencent Hy@TencentHunyuan

2026.09.22 08:53

The AI says the site is done. Then the homepage errors, the buttons overlap, and it added a login flow you never asked for. 🙃 Introduces WebCraftBench: agents actually use the live app, coverage-guided exploration finds what never got reached, then we score aesthetics, usability, and whether the original request was met. On 197 human-validated pairs, it matches human preference 85.3% of the time. Paper: