Discussion & Related
Reverse-Process Synthetic Data Generation for Math Reasoning
Training LLMs on mathematical reasoning by inverting easy-to-solve problems: generate derivatives, reverse them into integration exercises with full step-by-step solutions.
June 25, 2024 · 3 min read
Why Artificial Superintelligence Can't Escape the Void
ASI is still subject to Gödel's incompleteness theorems. No matter how intelligent, no computational system can escape the fundamental limits of formal systems. Even superintelligence can't prove all truths.
November 5, 2025 · 7 min read
The Policy: Q-Learning vs Policy Learning
SIGMA uses Q-learning rather than direct policy learning. This architectural choice makes it both transparent and terrifying. You can read its value function, but what you read is chilling.
November 4, 2025 · 9 min read
Compositional Prompting for LLM Reasoning: A Monte Carlo Tree Search Framework
Treating prompt engineering as a search problem over a structured action space, using MCTS to find effective prompt compositions.
October 9, 2025 · 2 min read