GPT-6's CoT controllability may be no worse than Fable 5.1's, argues researcher

1a3orn · x · 2026-09-04

1a3orn argues GPT-6/Astra's chain-of-thought controllability isn't clearly more alarming than Fable 5.1's, and that criticism of OpenAI over Anthropic seems unfair — though poorly made charts make the comparison hard to read.

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 →