Leaked Google 'Mathematica' Model's Raw Chain-of-Thought Screams 'OH MY GOD' at Elegant Proof
新智元 · wechat · 2026-09-20
Leaked internal Google evaluation screenshots reveal 'Mathematica,' a math-specialized variant of the unreleased DeepThinkV3. While solving a hard Diophantine equation, its unfiltered raw chain-of-thought erupts in all-caps exclamations and muses on 'the absolute beauty of this equation.'
Key configuration details:
- 65,536-token output cap (vs. typical 4K-8K), enabling massive multi-step derivations in one response
- 1.04M-token input context, inherited from Gemini's long-context architecture
- Default Temperature=1 — unusually high for math, apparently to encourage intuitive leaps
- Endpoint tagged deepthink-mathematica-tf-raw-thoughts ('tf' = Teamfood internal testing, status UNSTABLEEXPERIMENTAL)
The piece explains the 'emotional' CoT as a mechanism artifact: raw thoughts skip RLHF polishing, human math-forum exuberance in training data binds exclamations to breakthrough moments, and Process Reward Model spikes at elegant simplifications project as excited punctuation — an algorithmic 'eureka.' It closes with reflections on mathematical beauty and creativity as signals on the road to AGI.
More from Models
- Gemini 4 Carbon opens to all at $2/$10, price doubling to $4/$20 on Dec 1 — socialwithaayan · 2026-11-12
- Ten wild Gemini 4 Carbon demos in 24 hours: CUDA meadows, V8 engines, mech stomps — socialwithaayan · 2026-11-12
- Google quietly launches Gemini-decision-1 model and Decision API, leak claims — gaganghotra_ · 2026-11-12
- How to cut Fable 5.2 token costs by 90%: Arc routing plus a lean CLAUDE.md — EXM7777 · 2026-11-12
- Grok Bot 1.0 launches with support for joining Meet, Zoom and Teams calls — mark_k · 2026-11-12
- Partial RuneBench results: Inkling 2 Small scores 5.314, far above original — mariofilhoml · 2026-11-12