ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Researchers introduce the Design Creativity Bench to evaluate frontier AI models on UI design tasks. The study tested 16 models across 80 tasks, finding the best model, GPT-6 Astra, scored 65.5 against a human reference of 92.3. The team measures originality, creative range, and appropriateness to quantify design gaps.
Tap to vote and see what everyone thinks.
Summary by ByteBrief