Feng Ye
Butterfly - Machine Learning Capabilities
Input: (((36002--20+-6062327--15)--87)-8027)
Step-by-Step Solution:
= ( ( 3 6 0 0 2 - - 2 0 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 ) - 8 0 2 7
= ( 3 6 0 0 2 - - 2 0 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 - 8 0 2 7
= ( 3 6 0 2 2 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 - 8 0 2 7
= ( - 6 0 2 6 3 0 5 - - 1 5 ) - - 8 7 - 8 0 2 7
= - 6 0 2 6 3 0 5 - - 1 5 - - 8 7 - 8 0 2 7
= - 6 0 2 6 2 9 0 - - 8 7 - 8 0 2 7
= - 6 0 2 6 2 0 3 - 8 0 2 7
= - 6 0 3 4 2 3 0 <eos>
Metrics: Loss: 0.0068 | Accuracy: 100.00% (195/195) | Confidence: 99.52%
Current AI models struggle with:
We need models that think mathematically, not just compute.
System evolved from prototype to 3000+ lines of production code in ~48 hours
Code 99% generated by Gemini-2.5-Pro using Cursor
Example for expression: 23 - (5 + 7)
Note: Structural Level ID assignments evolve as our parser improves.
Input: (((36002--20+-6062327--15)--87)-8027)
CoT Steps:
= ( ( 3 6 0 0 2 - - 2 0 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 ) - 8 0 2 7
= ( 3 6 0 0 2 - - 2 0 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 - 8 0 2 7
= ( 3 6 0 2 2 + - 6 0 6 2 3 2 7 - - 1 5 ) - - 8 7 - 8 0 2 7
= ( - 6 0 2 6 3 0 5 - - 1 5 ) - - 8 7 - 8 0 2 7
= - 6 0 2 6 3 0 5 - - 1 5 - - 8 7 - 8 0 2 7
= - 6 0 2 6 2 9 0 - - 8 7 - 8 0 2 7
= - 6 0 2 6 2 0 3 - 8 0 2 7
= - 6 0 3 4 2 3 0 <eos>
Generated CoT enables:
Stage | Complexity | Example |
---|---|---|
1 | Single-digit addition | 2+3 |
4 | Negative numbers | -25+17 |
15 | Parentheses | (45-12)+(82-3) |
51 | Complex expressions | (((36002--20+-6062327--15)--87)-8027) |
Future | Physics equations | F = m·a, E = mc² |
Current: Linear progression
Future: Graph-based curriculum with model-chosen paths
Future: Graph-based curriculum with self-directed learning paths.
Key insight: Domain-specific architecture achieves superior mathematical reasoning with deterministic, reliable outputs.
Investigating whether specialized architectures can compete with general models
We've demonstrated that:
Mathematics as the foundation of genuine AI understanding.
Our approach builds systematic mathematical cognition from first principles.
Live Training Demonstration
Watch the model learn complex mathematical reasoning in real-time
Current Model:
Stage 51+ | 13-15M Parameters | d_model=512 | 4 Layers | Fully Deterministic
Dynamic curriculum learning with self-adapting architecture
Feng Ye
Butterfly - Machine Learning Capabilities
Pretraining on math & physics, post-training on human languages
(Warning: May be slow on your Mac 😅)