Leaked Anthropic Fable 5 Internal Chain of Thought
mark_k · x · 2026-07-06
Another suspected leak of Anthropic Fable 5's internal CoT reasoning trace has surfaced, despite such traces being highly guarded secrets among AI companies.
Compared to previous leaks, this trace reads more like natural English rather than abstract jargon, revealing Claude weighing different ideas and thinking out loud.
Each trace ends with the </thinking> closing tag, which is viewed as strong proof of its authenticity.
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26