Why Fable and Astra ship without a non-thinking mode: attack surface and CoT monitoring
maksym_andr · x · 2026-09-17
A thread speculates why Fable and Astra have no non-thinking mode: it would leak model size/depth, widen the attack surface, and a weak non-CoT Fable could undermine hidden CoT monitoring (only Fable can read its own hidden CoT). A reply adds that OpenAI and Ant both rely heavily on CoT monitoring and that a zero-thinking model is odd in 2026.
Related event: Frontier LLMs Nail 20-Digit Multiplication Without Tools(9 posts)→
More from Models
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02