Article List

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

Clear Filters
ML Products

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

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

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

Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge

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

1 year, 3 months ago Eugene Yan
62 words 1 min
ML Products

Building the Same App Using Various Web Frameworks

FastAPI, FastHTML, Next.js, SvelteKit, and thoughts on how coding assistants influence builders' choices....

1 year, 4 months ago Eugene Yan
93 words 1 min
ML Products

Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-…

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

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

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....

1 year, 6 months ago Eugene Yan
85 words 1 min
ML Products

AI Engineer 2024 Keynote - What We Learned from a Year of L…

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

1 year, 6 months ago Eugene Yan
87 words 1 min
ML Products

Netflix PRS 2024 - Applying LLMs to Recommendation Experien…

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

1 year, 7 months ago Eugene Yan
77 words 1 min
ML Products

Prompting Fundamentals and How to Apply them Effectively

Structured input/output, prefilling, n-shots prompting, chain-of-thought, reducing hallucinations, etc....

1 year, 7 months ago Eugene Yan
95 words 1 min
ML Products

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....

1 year, 8 months ago Eugene Yan
86 words 1 min
ML Products

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....

1 year, 9 months ago Eugene Yan
75 words 1 min
ML Products

Task-Specific LLM Evals that Do & Don't Work

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

1 year, 9 months ago Eugene Yan
84 words 1 min
ML Products

Don't Mock Machine Learning Models In Unit Tests

How unit testing machine learning code differs from typical software practices...

1 year, 10 months ago Eugene Yan
68 words 1 min
ML Products

How to Generate and Use Synthetic Data for Finetuning

Overcoming the bottleneck of human annotations in instruction-tuning, preference-tuning, and pretraining....

1 year, 11 months ago Eugene Yan
95 words 1 min
ML Products

Language Modeling Reading List (to Start Your Paper Club)

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

2 years ago Eugene Yan
74 words 1 min
ML Products

2023 Year in Review

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

2 years ago Eugene Yan
73 words 1 min
ML Products

Push Notifications: What to Push, What Not to Push, and How…

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

2 years ago Eugene Yan
90 words 1 min
ML Products

Out-of-Domain Finetuning to Bootstrap Hallucination Detecti…

How to use open-source, permissive-use data and collect less labeled samples for our tasks....

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

Reflections on AI Engineer Summit 2023

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

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