Data Science Current

AI Engineer 2025 - Improving RecSys & Search with LLM techniques

Eugene Yan

JUNE 3, 2025

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

AI

AI AI

Qualities and Behaviors of Exceptional Leaders

Eugene Yan

MAY 17, 2025

What makes a good leader? What do good leaders do? And wartime vs. peacetime leaders.

Building News Agents with MCP, Amazon Q CLI, and tmux

Eugene Yan

MAY 3, 2025

Automating my daily news flash via agentic workflows with Amazon Q CLI and MCPs

Webinars

What’s New in Apache Airflow® 3.0—And How Will It Reshape Your Data Workflows?

MORE WEBINARS

Stop Blaming the LLM-as-Judge; Fix Your Process Instead

Eugene Yan

APRIL 19, 2025

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

AI

AI AI

Frequently Asked Questions about My Writing Process

Eugene Yan

MARCH 29, 2025

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

Frequently Asked Questions On My Writing Process

Eugene Yan

MARCH 29, 2025

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

NVIDIA GTC - Building LLM-Powered Applications

Eugene Yan

MARCH 17, 2025

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

Improving Recommender Systems & Search in the Age of LLMs

Eugene Yan

MARCH 15, 2025

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

Building AI Reading Club: Features & Behind the Scenes

Eugene Yan

JANUARY 11, 2025

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

AI

AI AI

2024 Year in Review

Eugene Yan

DECEMBER 21, 2024

A peaceful year of steady progress on my craft and health

Some Paradoxical Rules of Writing

Eugene Yan

NOVEMBER 30, 2024

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

How to Run a Paper Club and Learn With Your Peers

Eugene Yan

NOVEMBER 23, 2024

Description of post here (150 chars)

A Minimal Mac Setup Guide

Eugene Yan

NOVEMBER 16, 2024

Setting up my new MacBook Pro from scratch

39 Lessons from Industry ML Conferences in 2024

Eugene Yan

NOVEMBER 2, 2024

ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.

ML

ML ML

AlignEval: Building an App to Make Evals Easy, Fun, and Automated

Eugene Yan

OCTOBER 26, 2024

Look at and label your data, build and evaluate your LLM-evaluator, and optimize it against your labels.

Hackathon Judge - Weights & Biases LLM-Evaluator Hackathon

Eugene Yan

SEPTEMBER 21, 2024

Being a human judge at the Weights & Biases LLM-as-a-Judge Hackathon

Building the Same App across Various Web Frameworks

Eugene Yan

SEPTEMBER 7, 2024

Comparing five implementations built with FastAPI, FastHTML, Next.

Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)

Eugene Yan

AUGUST 17, 2024

Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.

How to Interview and Hire ML/AI engineers

Eugene Yan

JULY 6, 2024

What to interview for, how to structure the phone screen, interview loop, and debrief, and a few tips.

ML

ML ML AI AI

AIE World's Fair 2024 Keynote - What We Learned from a Year of LLMs

Eugene Yan

JUNE 26, 2024

Special double-feature closing keynote from the 6 authors of the hit O'Reilly article on Applied LLMs.

Netflix PRS 2024 - Applying LLMs to Recommendation Experiences

Eugene Yan

MAY 30, 2024

Challenges and lessons from deploying LLM experiences: evals, scalability, guardrails.

What We've Learned From A Year of Building with LLMs

Eugene Yan

MAY 11, 2024

From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy.

Effective Prompting with A Handful of Fundamentals

Eugene Yan

MAY 25, 2024

Description of post here (150 chars)

Taming my Monkey Mind: How I Built a 24/7 AI Coach

Eugene Yan

APRIL 6, 2024

Building an AI coach with speech-to-text, text-to-speech, an LLM, and a virtual number.

AI

AI AI

A Builder's Guide to Evals for LLM-based Applications

Eugene Yan

MARCH 30, 2024

Evals for classification, summarization, translation, copyright regurgitation, and toxicity.

How to Unit Test Machine Learning Code & Models

Eugene Yan

FEBRUARY 24, 2024

How it differs from unit testing typical software and some guidelines

Machine Learning

Machine Learning Machine Learning

How to Generate Synthetic Data for Pretraining and Finetuning

Eugene Yan

FEBRUARY 10, 2024

Distillation vs. self-improvement across the three stages of language model training.

Language Modeling Reading List (to Start Your Paper Club)

Eugene Yan

JANUARY 6, 2024

Some fundamental papers and a one-sentence summary for each; start your own paper club!

2023 in Review

Eugene Yan

DECEMBER 30, 2023

An expanded charter, lots of writing and speaking, and finally learning to snowboard.

Push Notifications - What to Push, What Not to Push, and How Often

Eugene Yan

DECEMBER 23, 2023

Sending helpful & engaging pushes, filtering annoying pushes, and finding the frequency sweet spot.

Finetuning on Out-of-Domain Data to Detect Factual Inconsistency

Eugene Yan

NOVEMBER 4, 2023

Or how we can bootstrap on open-source, permissive-use data and collect less labeled samples.

Reflections on AI Engineer Summit 2023

Eugene Yan

OCTOBER 14, 2023

The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic.

AI

AI AI

Reflection and Takeaways from AI Engineer Summit 2023

Eugene Yan

OCTOBER 14, 2023

The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic.

AI

AI AI

AI Engineer Summit - Building Blocks for LLM Systems & Products

Eugene Yan

OCTOBER 8, 2023

I give one talk a year and in 2023 this is that talk.

AI

AI AI

Abstractive Summaries: Evaluation & Hallucination Detection

Eugene Yan

SEPTEMBER 2, 2023

Reference, context, and preference-based metrics, self-consistency, and catching hallucinations.

How to Match LLM Patterns to Problems

Eugene Yan

AUGUST 12, 2023

Distinguishing problems with external vs.

Design Patterns for LLM Systems & Products

Eugene Yan

JULY 29, 2023

Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.

Raspberry-LLM - Making My Raspberry Pico a Little Smarter

Eugene Yan

APRIL 15, 2023

Generating Dr. Seuss headlines, fake WSJ quotes, HackerNews troll comments, and more.

Obsidian-Copilot: A Prototype Assistant for Writing & Thinking

Eugene Yan

JUNE 10, 2023

Writing drafts via retrieval-augmented generation. Also reflecting on the week's journal entries.

Some Intuition on Attention and the Transformer

Eugene Yan

MAY 20, 2023

What's the big deal, intuition on query-key-value vectors, multiple heads, multiple layers, and more.

Open-LLMs - A list of LLMs for Commercial Use

Eugene Yan

MAY 6, 2023

It started with a question that had no clear answer, and led to eight PRs from the community.

Interacting with LLMs with Minimal Chat

Eugene Yan

MAY 6, 2023

Should chat be the main UX for LLMs? I don't think so and believe we can do better.

More Design Patterns For Machine Learning Systems

Eugene Yan

APRIL 22, 2023

9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more.

Machine Learning

Machine Learning Machine Learning

How LLM Apps can Help Us Research, Reflect, and Plan

Eugene Yan

APRIL 8, 2023

Also, shortcomings in document retrieval and how to overcome them.

Eugene Yan

AI Engineer 2025 - Improving RecSys & Search with LLM techniques

Qualities and Behaviors of Exceptional Leaders

Webinars

Trending Sources

Building News Agents with MCP, Amazon Q CLI, and tmux

Webinars

Stop Blaming the LLM-as-Judge; Fix Your Process Instead

Frequently Asked Questions about My Writing Process

Frequently Asked Questions On My Writing Process

NVIDIA GTC - Building LLM-Powered Applications

Improving Recommender Systems & Search in the Age of LLMs

Building AI Reading Club: Features & Behind the Scenes

2024 Year in Review

Some Paradoxical Rules of Writing

How to Run a Paper Club and Learn With Your Peers

A Minimal Mac Setup Guide

39 Lessons from Industry ML Conferences in 2024

AlignEval: Building an App to Make Evals Easy, Fun, and Automated

Hackathon Judge - Weights & Biases LLM-Evaluator Hackathon

Building the Same App across Various Web Frameworks

Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)

How to Interview and Hire ML/AI engineers

AIE World's Fair 2024 Keynote - What We Learned from a Year of LLMs

Netflix PRS 2024 - Applying LLMs to Recommendation Experiences

What We've Learned From A Year of Building with LLMs

Effective Prompting with A Handful of Fundamentals

Taming my Monkey Mind: How I Built a 24/7 AI Coach

A Builder's Guide to Evals for LLM-based Applications

How to Unit Test Machine Learning Code & Models

How to Generate Synthetic Data for Pretraining and Finetuning

Language Modeling Reading List (to Start Your Paper Club)

2023 in Review

Push Notifications - What to Push, What Not to Push, and How Often

Finetuning on Out-of-Domain Data to Detect Factual Inconsistency

Reflections on AI Engineer Summit 2023

Reflection and Takeaways from AI Engineer Summit 2023

AI Engineer Summit - Building Blocks for LLM Systems & Products

Abstractive Summaries: Evaluation & Hallucination Detection

How to Match LLM Patterns to Problems

Design Patterns for LLM Systems & Products

Raspberry-LLM - Making My Raspberry Pico a Little Smarter

Obsidian-Copilot: A Prototype Assistant for Writing & Thinking

Some Intuition on Attention and the Transformer

Open-LLMs - A list of LLMs for Commercial Use

Interacting with LLMs with Minimal Chat

More Design Patterns For Machine Learning Systems

How LLM Apps can Help Us Research, Reflect, and Plan

Stay Connected