Advancing Mathematical Reasoning in AI: Introducing Reverse-Process Synthetic Data Generation
A reverse-process approach to synthetic data generation for training LLMs on mathematical reasoning, producing step-by-step solutions from worked examples.
Browse posts by tag
A reverse-process approach to synthetic data generation for training LLMs on mathematical reasoning, producing step-by-step solutions from worked examples.
History of mathematical ideas underlying generic programming. More accessible than EoP.
A C++17 header-only library implementing Computational Basis Transforms - a unified framework for understanding how FFT, logarithmic arithmetic, and Bayesian inference are all instances of the same pattern.
A powerful symbolic expression toolkit for rule-based term rewriting with pattern matching, multiple input formats, and an interactive REPL.
How The Mocking Void's arguments about computational impossibility connect to Echoes of the Sublime's practical horror of exceeding cognitive bandwidth.
The formal foundations of cosmic dread. Lovecraft's horror resonates because it taps into something mathematically demonstrable: complete knowledge is impossible — not as humility, but as theorem.
How mathematical principles of generality, composability, invariants, and minimal assumptions translate into elegant software design.
Post-mortem on completing a mathematics master's degree over three years while navigating cancer treatment—what worked, what didn't, and lessons learned.
Why I chose to pursue a second master's in Mathematics and Statistics after my CS degree—seeking deeper foundations for statistical theory and inference.
Reflections on mathematical beauty—generality, inevitability, compression, and surprise—and why abstraction matters for software design.