跳到正文
Aran Komatsuzaki· @arankomatsuzaki · X·· 3 天前AI 评分38
AI 导读

Contra Labs 关于 AI 设计的有趣结果。专业设计师对真实客户简报进行盲选,人类在 76% 的对比中胜出,Fable 5.2 是表现最好的模型。 说实话,差距比预期小得多,Kimi K3.1 看起来也很棒。 抽奖活动:请回答如何辨别设计是否由 AI 制作。

正文 · 原文

Interesting result from Contra Labs on AI design. Pro designers voted blind on real client briefs, and humans still win 76% of comparisons, with Fable 5.2 the best model.

Honestly, the margin is much smaller than expected, and Kimi K3.1 seems great.

Giveaway for your answer to how you can tell a design was made by AI.

引用ben@contraben
The AI industry has a benchmarking problem. We're letting random people on the internet decide which models are best even for capabilities like design... So we built something different. Introducing The Frontier Design Benchmark from @contralabs https://contralabs.com/frontierdesign
在 X 查看被引用的帖子

来源:Aran Komatsuzaki · x.com