Latest writing
All posts →MCTS and AlphaZero - Four Steps in the Dark
Monte Carlo tree search never enumerates and never finishes. AlphaZero turned its visit counts into a training target and stopped asking humans.
Jev - The Classifier Strikes Back
Jev returns typed, calibrated decisions instead of text. Underneath, it looks like a very good zero-shot classifier, and calibration is the claim to test.
Mamba - Is Attention All You Really Need? Part 2
Selection broke the convolution that made state space models fast to train. Here is how Mamba got the speed back, and why attention stayed in the room.
Mamba - Is Attention All You Really Need? Part 1
State space models come from control theory, run like an RNN and train like a CNN. Mamba's one change lets each word decide what the model remembers.
Selected projects
All projects →Legal Research Assistant
On the cover: Legal Research Assistant Platform This project was delivered for MiAI.law, an Australian legal technology firm, to build a modern AI-driven system f...
AI-Driven Quantitative Risk Analysis
On the cover: Digitized Process Flow Diagram (PFD) with highlighted Elementary Process Sections (EPS) and graph This work was conducted at Saudi Aramco. The proje...