Same Parts, Different Wiring: Mechanistic Interpretability of Moral Fine-Tuning
An exploration of how moral fine-tuning changes LLMs
Deep Learning
Deep learning notes and projects covering neural networks, sequence models, language models, generative modeling, and interpretability.
Neural networks, mostly the language side of them. There's writing on search and semantic search, how language models work, a survey of text diffusion, and some interpretability work that looks at what a model has actually learned.
It overlaps a lot with the machine learning page. This is the part that's specifically about deep learning and language models.
FlashAttention & LLM Inference on GPUs
Writing a FlashAttention CUDA kernel from scratch, tiling the attention matrix to avoid materializing N×N memory, building a KV cache for token generation, and running GPT-2 with custom kernels end-to-end.
Hierarchical Reasoning Models
A talk exploring novel neural architectures for complex reasoning tasks, featuring two-level recurrence and adaptive computation.
Reflections on ICML 2025
Some notes and observations from my time at the 2025 International Conference for Machine Learning (ICML)
Language Diffusion Survey
A talk surveying diffusion models for language, from DDPM foundations to modern mask diffusion competing with auto-regressive models.
Semantic Search
What's an embedding vector, and how can we use neural networks to improve the relevance of search results?
Language Models
From n-grams to ChatGPT, how language models work and how they can be used to solve real-world problems.
Search Engine Fundamentals
Essential terms and concepts of how search works. Queries, indexes, & relevance.