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.)
Google released Android Bench 2.0 today, introducing long-horizon tasks and agentic evaluation for AI models. The dashboard now lists Gemini 3.8 Flash, GPT-6, and others, with Claude Opus 5.5 leading at a 32% pass rate for complex engineering work.
Tap to vote and see what everyone thinks.
Summary by ByteBrief