Patterns for Building Cybersecurity Evals
A sandboxed target, inputs that influence task difficulty, tools, and a grader.
Eugene Yan
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
Using LLMs to Secure Source Code
Build a threat model, discover vulnerabilities, verify, triage, and patch.
How to Work and Compound with AI
Context as infra, taste as config, verification for autonomy, scale via delegation, closing the loop.
2025 Year in Review
An eventful year of progress in health and career, while making time for travel and reflection.
Product Evals in Three Simple Steps
Label some data, align LLM-evaluators, and run the eval harness with each change.
Advice for New Principal Tech ICs (i.e., Notes to Myself)
Based on what I've learned from role models and mentors in Amazon
Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
An LLM that can converse in English & item IDs, and make recommendations w/o retrieval or tools.
Evaluating Long-Context Question & Answer Systems
Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.
Exceptional Leadership: Some Qualities, Behaviors, and Styles
What makes a good leader? What do good leaders do? And commando, soldier, and police leadership.
Building News Agents for Daily News Recaps with MCP, Q, and tmux
Learning to automate simple agentic workflows with Amazon Q CLI, Anthropic MCP, and tmux.
An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Applying the scientific method, building via eval-driven development, and monitoring AI output.
Frequently Asked Questions about My Writing Process
How I started, why I write, who I write for, how I write, and more.
NVIDIA GTC 2025 - Building LLM-Powered Applications
Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025.
Improving Recommendation Systems & Search in the Age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
Building AI Reading Club: Features & Behind the Scenes
Exploring how an AI-powered reading experience could look like.
2024 Year in Review
A peaceful year of steady progress on my craft and health.
Seemingly Paradoxical Rules of Writing
With regard to writing, there are many rules and also no rules at all.
How to Run a Weekly Paper Club (and Build a Learning Community)
Benefits of running a weekly paper club, how to start one, and how to read and facilitate papers.
My Minimal MacBook Pro Setup Guide
Setting up my new MacBook Pro from scratch
39 Lessons on Building ML Systems, Scaling, Execution, and More
ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.
AlignEval: Building an App to Make Evals Easy, Fun, and Automated
Look at and label your data, build and evaluate your LLM-evaluator, and optimize it against your labels.
Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge
Being a human judge at the Weights & Biases LLM-as-a-Judge Hackathon
Building the Same App Using Various Web Frameworks
FastAPI, FastHTML, Next.js, SvelteKit, and thoughts on how coding assistants influence builders' choices.
Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)
Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.
How to Interview and Hire ML/AI Engineers
What to interview for, how to structure the phone screen, interview loop, and debrief, and a few tips.
AI Engineer 2024 Keynote - What We Learned from a Year of LLMs
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
Challenges and lessons from deploying LLM experiences: evals, scalability, guardrails.
Prompting Fundamentals and How to Apply them Effectively
Structured input/output, prefilling, n-shots prompting, chain-of-thought, reducing hallucinations, etc.
What We've Learned From A Year of Building with LLMs
From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy.
Building an AI Coach to Help Tame My Monkey Mind
Building an AI coach with speech-to-text, text-to-speech, an LLM, and a virtual number.
Task-Specific LLM Evals that Do & Don't Work
Evals for classification, summarization, translation, copyright regurgitation, and toxicity.
Don't Mock Machine Learning Models In Unit Tests
How unit testing machine learning code differs from typical software practices
How to Generate and Use Synthetic Data for Finetuning
Overcoming the bottleneck of human annotations in instruction-tuning, preference-tuning, and pretraining.
Language Modeling Reading List (to Start Your Paper Club)
Some fundamental papers and a one-sentence summary for each; start your own paper club!
2023 Year in Review
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
Sending helpful & engaging pushes, filtering annoying pushes, and finding the frequency sweet spot.
Out-of-Domain Finetuning to Bootstrap Hallucination Detection
How to use open-source, permissive-use data and collect less labeled samples for our tasks.
Reflections on AI Engineer Summit 2023
The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic.
AI Engineer 2023 Keynote - Building Blocks for LLM Systems
Evals, retrieval-augmented generation, guardrails, and collecting feedback; all that good stuff.
Evaluation & Hallucination Detection for Abstractive Summaries
Reference, context, and preference-based metrics, self-consistency, and catching hallucinations.
How to Match LLM Patterns to Problems
Distinguishing problems with external vs. internal LLMs, and data vs non-data patterns
Patterns for Building LLM-based Systems & Products
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
Obsidian-Copilot: An Assistant for Writing & Reflecting
Writing drafts via retrieval-augmented generation. Also reflecting on the week's journal entries.
Some Intuition on Attention and the Transformer
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
It started with a question that had no clear answer, and led to eight PRs from the community.
Interacting with LLMs with Minimal Chat
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
9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more.
Raspberry-LLM - Making My Raspberry Pico a Little Smarter
Generating Dr. Seuss headlines, fake WSJ quotes, HackerNews troll comments, and more.
Experimenting with LLMs to Research, Reflect, and Plan
Also, shortcomings in document retrieval and how to overcome them with search & recsys techniques.