CoT controllability dips slightly in GPT-6.2 Astra, median-length comparison worries researcher

tomekkorbak · x · 2026-11-18

Thread follow-up: CoT controllability is slightly lower for 6.2 Astra than 6 Astra, which helps monitorability. But the author argues what matters in practice is controllability at each model's median CoT length — and since 6.2's CoTs are shorter, that metric may also be worsening; he'd like to see it plotted.

Original post →

More from Models

Models channel →