Same Parts, Different Wiring: Mechanistic Interpretability of Moral Fine-Tuning
An exploration of how moral fine-tuning changes LLMs
Machine Learning
Machine learning notes, course projects, and research writeups on supervised learning, data analysis, evaluation, and model behavior.
Two things, mostly. I took a graduate ML course and wrote up a retrospective that covers the whole thing: supervised learning, reinforcement learning, and the theory behind them. The other posts are notes from papers I've read and topics I keep coming back to.
This is the general-purpose end of what I work on. Deep learning, GPUs, and AI safety have their own pages.
Thread Retro 1 part
Updated
GPU Hardware and Software
What I Learned in GPU Hardware and Software (CS 8803) - A Retrospective
Notes on Effective ML Research
A summary of my takeaways from three influential articles on conducting effective empirical AI alignment research.
BlueDot AI Safety Evals Paper Club Notes
My notes and takeaways from the BlueDot AI Safety Evals paper club, covering recent papers on AI alignment, security, and evaluations.
Hierarchical Reasoning Models
A talk exploring novel neural architectures for complex reasoning tasks, featuring two-level recurrence and adaptive computation.
Thread Retro 1 part
Updated
Machine Learning
A survey of concepts covered in my graduate Machine Learning course
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.