profile

Eugene Yan

Some Paradoxical Rules of Writing

Published about 1 year ago • 1 min read

Hey friends,

A very short email this week. I've been thinking a lot about writing lately and I've come to realize that there are a lot of rules, and at the same time no rules, about writing.

I appreciate you receiving this, but if you want to stop, simply unsubscribe.

• • •

  • use simple words to be clear and concise
  • use complex words to be sharp and precise

​

  • write short sentences for the punch
  • write long sentences to convey nuance

​

  • spend 80% effort on an intro that hooks
  • skip the intro, just get into the nooks

​

  • write for a wide audience to maximize reach
  • write for an audience of one—dive into a niche

​

  • write about something that may seem plain
  • write about something that’s outright arcane

​

  • write what’s widely known in a fresh way
  • write what no one cares about or dares say

​

  • make it easy to read but hard to forget
  • make it deep and detailed so readers sweat

​

  • condense wisdom into 120 words that zing
  • expand over 12,000 words and let your thoughts sing

​

  • write without publishing to hone your craft
  • hit publish even though it still feels like a draft

​

  • emulate the style of others to learn and grow
  • find and hone your voice and let it flow

​

  • spend weeks and months polishing a piece
  • ship something in hours, just release

​

  • ask for feedback to gain the wisdom of the crowd
  • trust your inner voice and think out loud

​

  • follow the rules
  • break the rules

​

Eugene Yan

Applied Scientist @ Amazon, Writer & Speaker, Operator-Angel

I build ML, RecSys, and LLM systems that serve customers at scale, and write about what I learn along the way. Join 7,500+ subscribers!

Read more from Eugene Yan

Hey friends, After repeating myself for the nth time on how to build product evals, I figured I should write it down. There are three basic steps: (i) labeling a small dataset, (ii) aligning our LLM evaluators, and (iii) running the experiment + evaluation harness with each config change. I appreciate you receiving this, but if you want to stop, simply unsubscribe. • • • 👉 Read in browser for best experience (web version has extras & images) 👈 First, label some data It begins with sampling...

8 days ago • 7 min read

Hey friends, What makes an effective principal engineer or scientist? I’ve distilled what I’ve observed from role models and quoted some of their advice below. While my perspective is Amazon-centric, these ideas should also apply to most principal tech IC roles. As always, use your best judgment and assess if this advice applies to you and your situation. I appreciate you receiving this, but if you want to stop, simply unsubscribe. 👉 Read in browser for best experience (web version has extras...

about 2 months ago • 11 min read

Hi friends, I got nerdsniped when I first heard about Semantic IDs. The idea is simple: Instead of using random hash IDs for videos or songs or products, we can use semantically meaningful tokens that an LLM can natively understand. I wondered, could we train an LLM-recommender hybrid on the rich behavioral data that makes today’s recommender systems so effective? I appreciate you receiving this, but if you want to stop, simply unsubscribe. • • • 👉 Read in browser for best experience (web...

3 months ago • 17 min read