Every's Hands-On: Astra 6.2 Regresses in Writing, Falls Short in Coding

After weeks of testing by its 30-person team, Every found OpenAI's Astra 6.2 and Sol 6.2 disappointing versus Fable 5.2, with regressed writing, prematurely ended coding tasks, and no user retention.

2026-11-18 ~ 2026-11-18 · 3 related posts