1
The First Rule of Machine Learning: Start Without Machine Learning
Why this is the first rule, some baseline heuristics, and when to move on to machine learning.
Eugene Yan
I work to bridge the field and the frontier, and help build safe, reliable AI systems that scale. I also write and speak about AI-powered systems and products, and prototype for fun.
- Popular posts
- 18
- Total points
- 5,161
- HN comments
- 1,959
- Rank
- #208 personal
Visit eugeneyan.com → On Hacker News Mar 2020 – Oct 2025
AI & Machine Learning 7Life, Learning & Writing 4Web & Frontend 3Tools & Productivity 3Career & Management 3Software Engineering 2
2
Patterns for building LLM-based systems and products
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
3
Improving recommendation systems and search in the age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
4
5
Obsidian-Copilot: A Prototype Assistant for Writing and Thinking
Writing drafts via retrieval-augmented generation. Also reflecting on the week's journal entries.
6
Task-specific LLM evals that do and don't work
Evals for classification, summarization, translation, copyright regurgitation, and toxicity.
7
Experimenting with LLMs to Research, Reflect, and Plan
Also, shortcomings in document retrieval and how to overcome them with search & recsys techniques.