Article List

Explore latest news, discover interesting content, and dive deep into topics that interest you

Clear Filters
ML Products

AI Engineer 2023 Keynote - Building Blocks for LLM Systems

Evals, retrieval-augmented generation, guardrails, and collecting feedback; all that good stuff....

2 years, 3 months ago Eugene Yan
86 words 1 min
ML Products

Evaluation & Hallucination Detection for Abstractive Summar…

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

2 years, 4 months ago Eugene Yan
88 words 1 min
ML Products

How to Match LLM Patterns to Problems

Distinguishing problems with external vs. internal LLMs, and data vs non-data patterns...

2 years, 4 months ago Eugene Yan
75 words 1 min
ML Products

Patterns for Building LLM-based Systems & Products

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

2 years, 5 months ago Eugene Yan
79 words 1 min
ML Products

Obsidian-Copilot: An Assistant for Writing & Reflecting

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

2 years, 7 months ago Eugene Yan
86 words 1 min
ML Products

Some Intuition on Attention and the Transformer

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

2 years, 7 months ago Eugene Yan
88 words 1 min
ML Products

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....

2 years, 8 months ago Eugene Yan
76 words 1 min
ML Products

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....

2 years, 8 months ago Eugene Yan
66 words 1 min
ML Products

More Design Patterns For Machine Learning Systems

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

2 years, 8 months ago Eugene Yan
92 words 1 min
ML Products

Raspberry-LLM - Making My Raspberry Pico a Little Smarter

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

2 years, 8 months ago Eugene Yan
74 words 1 min
ML Products

Experimenting with LLMs to Research, Reflect, and Plan

Also, shortcomings in document retrieval and how to overcome them with search & recsys techniques....

2 years, 9 months ago Eugene Yan
88 words 1 min
ML Products

LLM-powered Biographies

Asking LLMs to generate biographies to get a sense of how they memorize and regurgitate....

2 years, 9 months ago Eugene Yan
74 words 1 min
ML Products

How to Write Data Labeling/Annotation Guidelines

Writing good instructions to achieve high precision and throughput....

2 years, 10 months ago Eugene Yan
59 words 1 min
ML Products

Content Moderation & Fraud Detection - Patterns in Industry

Collecting ground truth, data augmentation, cascading heuristics and models, and more....

2 years, 10 months ago Eugene Yan
76 words 1 min
3 / 3