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.)
Endor Labs' Agent Security League found GPT-5.5 scored 61.5% functional correctness in Codex and 87.2% in Cursor, a 25.7-point swing from the runtime alone. Input tokens are 86-98% of OpenRouter volume, so the harness controls most costs through cache discipline.
Tap to vote and see what everyone thinks.
Summary by ByteBrief