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.
This site uses cookies to improve your experience. To help us insure we adhere to various privacy regulations, please select your country/region of residence. If you do not select a country, we will assume you are from the United States. Select your Cookie Settings or view our Privacy Policy and Terms of Use.
Cookies and similar technologies are used on this website for proper function of the website, for tracking performance analytics and for marketing purposes. We and some of our third-party providers may use cookie data for various purposes. Please review the cookie settings below and choose your preference.
Used for the proper function of the website
Used for monitoring website traffic and interactions
Cookies and similar technologies are used on this website for proper function of the website, for tracking performance analytics and for marketing purposes. We and some of our third-party providers may use cookie data for various purposes. Please review the cookie settings below and choose your preference.
Eugene Yan
JUNE 3, 2025
Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.
Eugene Yan
MAY 17, 2025
What makes a good leader? What do good leaders do? And wartime vs. peacetime leaders.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Eugene Yan
MAY 3, 2025
Automating my daily news flash via agentic workflows with Amazon Q CLI and MCPs
Eugene Yan
APRIL 19, 2025
Applying the scientific method, building via eval-driven development, and monitoring AI output.
Eugene Yan
MARCH 29, 2025
How I started, why I write, who I write for, how I write, and more.
Eugene Yan
MARCH 29, 2025
How I started, why I write, who I write for, how I write, and more.
Eugene Yan
MARCH 17, 2025
Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025.
Eugene Yan
MARCH 15, 2025
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
Eugene Yan
JANUARY 11, 2025
Exploring how an AI-powered reading experience could look like.
Eugene Yan
DECEMBER 21, 2024
A peaceful year of steady progress on my craft and health
Eugene Yan
NOVEMBER 30, 2024
With regard to writing, there are many rules and also no rules at all.
Eugene Yan
NOVEMBER 23, 2024
Description of post here (150 chars)
Eugene Yan
NOVEMBER 16, 2024
Setting up my new MacBook Pro from scratch
Eugene Yan
NOVEMBER 2, 2024
ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.
Eugene Yan
OCTOBER 26, 2024
Look at and label your data, build and evaluate your LLM-evaluator, and optimize it against your labels.
Eugene Yan
SEPTEMBER 21, 2024
Being a human judge at the Weights & Biases LLM-as-a-Judge Hackathon
Eugene Yan
SEPTEMBER 7, 2024
Comparing five implementations built with FastAPI, FastHTML, Next.
Eugene Yan
AUGUST 17, 2024
Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.
Eugene Yan
JUNE 26, 2024
Special double-feature closing keynote from the 6 authors of the hit O'Reilly article on Applied LLMs.
Eugene Yan
MAY 30, 2024
Challenges and lessons from deploying LLM experiences: evals, scalability, guardrails.
Eugene Yan
MAY 11, 2024
From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy.
Eugene Yan
MAY 25, 2024
Description of post here (150 chars)
Eugene Yan
APRIL 6, 2024
Building an AI coach with speech-to-text, text-to-speech, an LLM, and a virtual number.
Eugene Yan
MARCH 30, 2024
Evals for classification, summarization, translation, copyright regurgitation, and toxicity.
Eugene Yan
FEBRUARY 24, 2024
How it differs from unit testing typical software and some guidelines
Eugene Yan
FEBRUARY 10, 2024
Distillation vs. self-improvement across the three stages of language model training.
Eugene Yan
JANUARY 6, 2024
Some fundamental papers and a one-sentence summary for each; start your own paper club!
Eugene Yan
DECEMBER 30, 2023
An expanded charter, lots of writing and speaking, and finally learning to snowboard.
Eugene Yan
DECEMBER 23, 2023
Sending helpful & engaging pushes, filtering annoying pushes, and finding the frequency sweet spot.
Eugene Yan
NOVEMBER 4, 2023
Or how we can bootstrap on open-source, permissive-use data and collect less labeled samples.
Eugene Yan
OCTOBER 14, 2023
The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic.
Eugene Yan
OCTOBER 14, 2023
The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic.
Eugene Yan
OCTOBER 8, 2023
I give one talk a year and in 2023 this is that talk.
Eugene Yan
SEPTEMBER 2, 2023
Reference, context, and preference-based metrics, self-consistency, and catching hallucinations.
Eugene Yan
AUGUST 12, 2023
Distinguishing problems with external vs.
Eugene Yan
JULY 29, 2023
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
Eugene Yan
APRIL 15, 2023
Generating Dr. Seuss headlines, fake WSJ quotes, HackerNews troll comments, and more.
Eugene Yan
JUNE 10, 2023
Writing drafts via retrieval-augmented generation. Also reflecting on the week's journal entries.
Eugene Yan
MAY 20, 2023
What's the big deal, intuition on query-key-value vectors, multiple heads, multiple layers, and more.
Eugene Yan
MAY 6, 2023
It started with a question that had no clear answer, and led to eight PRs from the community.
Eugene Yan
MAY 6, 2023
Should chat be the main UX for LLMs? I don't think so and believe we can do better.
Eugene Yan
APRIL 22, 2023
9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more.
Eugene Yan
APRIL 8, 2023
Also, shortcomings in document retrieval and how to overcome them.
Expert insights. Personalized for you.
We have resent the email to
Are you sure you want to cancel your subscriptions?
Let's personalize your content