Cross-model comparison suggests CoT controllability decline isn't OpenAI-specific

1a3orn · x · 2026-09-04

Thread conclusion: comparing against Claude, Fable 5.1 shows greater controllability than everything but Mythos preview, with the same worsening trend. The author concludes the CoT controllability decline is unlikely caused by OpenAI-specific looped transformers—unless his analysis is mistaken.

Related event: CoT steerability drops with length across GPT-6 and Fable 5.1, possibly industry-wide(6 posts)→

Original post →

More from Models

Models channel →