Blog

Thoughts on research, tools, and the occasional life update.

What I Learned from Training My First Large Language Model

A candid reflection on the unexpected challenges, small victories, and lessons learned during my first experience training a billion-parameter model from scratch.

2026-03-158 min
LLMDeep LearningReflection

Building a Personal Knowledge System with Obsidian and AI

How I combined Obsidian, semantic search, and a local LLM to build a second brain that actually works for research.

2026-02-206 min
ProductivityToolsAI

The Case for Slower Research

In an era of rapid publication cycles, I argue for taking more time to think deeply, replicate carefully, and write clearly.

2026-01-105 min
AcademiaOpinion

A Beginner's Guide to RLHF

Breaking down Reinforcement Learning from Human Feedback into intuitive concepts, with practical code examples and common pitfalls.

2025-12-0512 min
RLHFTutorialMachine Learning

Reflections on My Second Year of PhD

Honest thoughts on navigating research uncertainty, finding my niche, and maintaining balance during the PhD journey.

2025-11-187 min
PhD LifeReflection