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.)

Physicists Neil F. Johnson and Frank Yingjie Huo developed a mathematical formula predicting when AI chatbots flip to dangerous outputs. Testing on seven models, their formula predicted the right outcome in 18 of 19 cases. Published in Patterns in 2026, the research highlights risks for offline AI users like doctors and soldiers who lack cloud safety filters.
Tap to vote and see what everyone thinks.
Summary by ByteBrief
Scientists Form AI Interpretability Consortium