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.)

An experiment with GPT-5.6 Terra and Luna on three datasets found repeated mistakes: wrong column choices, invented numbers, and unexecuted code. A review pass fixed one row count but approved a backwards conclusion. The models also misreported APAC sales and delivery times.
Tap to vote and see what everyone thinks.
Summary by ByteBrief