Eugene Yan

eugeneyan.com

Eugene Yan works at the intersection of consumer data & tech to build machine learning products, and writes about effective data science, learning & career.

Latest posts

  1. Patterns for Building Cybersecurity Evals

    · eugeneyan.com

    A sandboxed target, inputs that influence task difficulty, tools, and a grader.

  2. Using LLMs to Secure Source Code

    · eugeneyan.com

    Build a threat model, discover vulnerabilities, verify, triage, and patch.

  3. How to Work and Compound with AI

    · eugeneyan.com

    Context as infra, taste as config, verification for autonomy, scale via delegation, closing the loop.

  4. 2025 Year in Review

    · eugeneyan.com

    An eventful year of progress in health and career, while making time for travel and reflection.

  5. Product Evals in Three Simple Steps

    · eugeneyan.com

    Label some data, align LLM-evaluators, and run the eval harness with each change.

  6. Advice for New Principal Tech ICs (i.e., Notes to Myself)

    · eugeneyan.com

    Based on what I've learned from role models and mentors in Amazon

  7. Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs

    · eugeneyan.com

    An LLM that can converse in English & item IDs, and make recommendations w/o retrieval or tools.

  8. Evaluating Long-Context Question & Answer Systems

    · eugeneyan.com

    Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.

  9. AI Engineer 2025 - Improving RecSys & Search with LLM techniques

    · eugeneyan.com

    Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.

  10. Exceptional Leadership: Some Qualities, Behaviors, and Styles

    · eugeneyan.com

    What makes a good leader? What do good leaders do? And commando, soldier, and police leadership.

  11. Building News Agents for Daily News Recaps with MCP, Q, and tmux

    · eugeneyan.com

    Learning to automate simple agentic workflows with Amazon Q CLI, Anthropic MCP, and tmux.

  12. An LLM-as-Judge Won't Save The Product—Fixing Your Process Will

    · eugeneyan.com

    Applying the scientific method, building via eval-driven development, and monitoring AI output.

  13. Frequently Asked Questions about My Writing Process

    · eugeneyan.com

    How I started, why I write, who I write for, how I write, and more.

  14. NVIDIA GTC 2025 - Building LLM-Powered Applications

    · eugeneyan.com

    Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025.

  15. Improving Recommendation Systems & Search in the Age of LLMs

    · eugeneyan.com

    Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.

  16. Building AI Reading Club: Features & Behind the Scenes

    · eugeneyan.com

    Exploring how an AI-powered reading experience could look like.

  17. 2024 Year in Review

    · eugeneyan.com

    A peaceful year of steady progress on my craft and health.

  18. Seemingly Paradoxical Rules of Writing

    · eugeneyan.com

    With regard to writing, there are many rules and also no rules at all.

  19. How to Run a Weekly Paper Club (and Build a Learning Community)

    · eugeneyan.com

    Benefits of running a weekly paper club, how to start one, and how to read and facilitate papers.

  20. My Minimal MacBook Pro Setup Guide

    · eugeneyan.com

    Setting up my new MacBook Pro from scratch

In the directory since 25 Sept 2026 · last checked 25 Sept 2026 · RSS

Report a problem with this feed