Published onJune 27, 2026Forward and Reverse KL DivergenceaillmmathA note on forward and reverse Kullback-Leibler divergence and how it relates to Reinforcement Learning training.
Published onJune 22, 2025Cross-Layer Transcoders and Sparse AutoencodersaillmclassicalSparse Autoencoders (SAEs) and Cross-Layer Transcoders (CLTs) are two approaches to interpretability of transformer models. Read up on what they're good for and how they differ.
Published onJune 18, 2025Emerging Principles of Agent DesignaillmclassicalPractical tips on how to design single and multi-agent systems. A synthesis of emerging principles and patterns as of June 2025.
Published onMay 13, 2025Induction Circuits - LLMs are more than next-token predictorsaillmclassicalThis blog post explores Induction Circuits, an example of a learned mini algorithm of transformer models that runs at inference time.
Published onMarch 26, 2025Vibe Coding a Quantum State SimulatorquantumaiI vibe coded a quantum state simulator, which I hope will be a useful resource for some of you learning about quantum computing.
