OpenAI & others quietly using loop transformers that hide their 'thinking'

realDanFu · x · 2026-09-03

Amir reports OpenAI and others are quietly using loop transformers that don't show their 'thinking' when scaled up — a leap in performance, but sparking security concerns inside and outside OpenAI. Rumors suggest the mysterious Astra is a looped model. Researcher haydenprairie points to his paper Parcae covering the math for stably training looped models, showing looping follows predictable scaling laws.

Related event: OpenAI's Astra Reportedly Reasons in Latent Space, Raising Safety Concerns(93 posts)→

Original post →

More from Models

Models channel →