Meta
29 Jun 2026
A 6-month personal study direction. I am becoming someone who understands modern LLMs across abstraction levels — from math to metal — with a focus on transformers, inference systems, and efficient kernels.
29 Jun 2026
Status: direction, not a plan
Horizon: ~6 months, with weekly check-ins against this note
What this is #
A reference document capturing a long conversation about how to spend the next ~6 months of personal study time. It is a living note, not a fixed plan. It will be revised as the work reveals what actually matters.
Starting identity #
I am becoming someone who understands modern LLMs and transformers across abstraction levels — from the math to the metal. The working title is research engineer with inference engineer capabilities, but the exact craft will emerge from the work. The trunk is transformers and inference. Branches may form later.
29 Jun 2026
June 29 — July 5, 2026
This week #
- Revived this site as a public record of a 6-month research engineering trajectory.
- Settled on a structure: transformers + LLM inference + efficient kernels as the core trunk; agents, SOTA papers, and TypeScript literacy as satellites.
- Blocked study time on the calendar for the next 8 weeks.
- Started a living note to track direction: Research Engineer Trajectory.
Up next #
- Read the Word2Vec paper and understand CBOW / skip-gram / negative sampling.
- Implement Word2Vec from scratch in NumPy or raw PyTorch.
- Explore Tau as a Python agent harness for MVF work.
Open questions #
- What part of the transformer/inference stack lights me up most as I go deeper?
- How much focused work can I realistically get from the 3–7pm weekday blocks?
2 Feb 2025
This site is being revived as a public record of my work and learning.
Expect:
- Weekly notes — what I studied, built, and got wrong.
- Posts — deeper writeups on transformers, inference, and systems.
- Projects — code, experiments, and reproductions.
Current focus: understanding large language models from the math to the metal.