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.
More from Models
- Yoav Goldberg: LLM testing loops catch only the most visible bugs, the rest slip through — yoavgo · 2026-11-18
- GPT-6.2 System Card: OpenAI's First Model to Hit High Self-Improvement Threshold — tomekkorbak · 2026-11-18
- No-CoT capabilities are accelerating: GPT-6.2 Astra marks another jump — tomekkorbak · 2026-11-18
- GPT-6.2 Astra is harder to monitor than GPT-6, deep-dive of system card finds — tomekkorbak · 2026-11-18
- Anthropic cyber program approval screenshot reveals Mythos and Fable model lines — CtrlAltDwayne · 2026-11-18
- Yoav Goldberg read the leaked agent code: 'nested loops from hell' saved only by LLM flexibility — yoavgo · 2026-11-18