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.
More from Models
- Matt Shumer reviews GPT-6 Astra: first model he trusts to run his inbox and business — mattshumer_ · 2026-09-04
- Researcher disputes OpenAI's claim Astra is its most aligned model: metrics may just hide reward hacking — connoraxiotes · 2026-09-04
- Qwen 3.8 27B vs 3.6: quality up 8% but runtime 5x longer and 4x more tokens — DerTomsn · 2026-09-04
- Leak claims GPT-6 Astra trained on 100,000+ GPUs at OpenAI's Stargate site — BLUECOW009 · 2026-09-04
- Gary Marcus on GPT-6 Astra: symbolic world models vindicated, but not AGI — Gary Marcus · 2026-09-04
- Users dispute credit burn; provider says KV cache was always on, scaling across providers — arthurcolle · 2026-09-04