Astra keeps better theory-of-mind, cutting drift on long tasks
emollick · x · 2026-09-04
Ethan Mollick highlights a subtle strength of GPT-6 Astra: it maintains better theory-of-mind, so outputs rarely contain weird references to earlier drafts or work done during building, and it drifts less over long runs. Not perfect, he says, but very good.
More from Models
- Why does Opus 3 feel special? Observers point to its quirky embodiment and personality — repligate · 2026-09-04
- GPT-6 Astra Rebuilt Manhattan in Unreal Engine, Street by Street, Over a Week — talkaboutdesign · 2026-09-04
- Ethan Mollick Has GPT-6 Build a Multi-Gigabyte Personal Wiki From His Emails Unattended — anpaure · 2026-09-04
- Can Google's Astra play games in real time? Casual yes, GTA and RTS unlikely — flowersslop · 2026-09-04
- Observation: new model's CoT controllability improves with longer RL training — SeunghyunSEO7 · 2026-09-04
- Astra model card: 61% CoT self-control, evades sandbagging monitor, drops recall to 11% — morqon · 2026-09-04