<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Writing on zhubert</title><link>https://zhubert.com/writing/</link><description>Recent content in Writing on zhubert</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Mon, 15 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://zhubert.com/writing/index.xml" rel="self" type="application/rss+xml"/><item><title>An Introduction to Transformers</title><link>https://zhubert.com/writing/intro-to-transformers/</link><pubDate>Mon, 15 Dec 2025 00:00:00 +0000</pubDate><guid>https://zhubert.com/writing/intro-to-transformers/</guid><description>I&amp;rsquo;ve been interested in Artificial Intelligence, through many different lenses, for quite some time. As a science fiction fan and one time author, it&amp;rsquo;s obviously a subject that&amp;rsquo;s been treated thoroughly from every angle. It&amp;rsquo;s good! It&amp;rsquo;s bad! It&amp;rsquo;s going to end humanity!
But it (&amp;ldquo;actual&amp;rdquo; AI) felt incredibly far away even just a few years ago. At that point in time, I did a bit of work in Text Classification and Object Detection and the results were definitely mixed.</description></item><item><title>A Little Bit of Slope Makes Up for a Lot of Y-Intercept</title><link>https://zhubert.com/writing/a-little-bit-of-slope/</link><pubDate>Fri, 10 Oct 2025 00:00:00 +0000</pubDate><guid>https://zhubert.com/writing/a-little-bit-of-slope/</guid><description>Years ago, I stumbled across a lecture by John Ousterhout. (You might know him as the creator of Tcl, or just as a general computer science luminary.) It was part of his weekend thought series, and one line has stuck with me ever since — straightforward, but the kind of thing that you see echo in many applications:
A little bit of slope makes up for a lot of y-intercept. By way of reminder, picture two lines on a graph.</description></item><item><title>The Power of Incremental Work</title><link>https://zhubert.com/writing/the-power-of-incremental-work/</link><pubDate>Thu, 08 Oct 2015 00:00:00 +0000</pubDate><guid>https://zhubert.com/writing/the-power-of-incremental-work/</guid><description>Quite a while ago, I wrote a review of The New Turing Omnibus. A very clever book whose double entendre title reinforced the wit with which the subject matter was to be handled. In short, a very fun book that covers a lot of Computer Science topics.
What’s interesting though is how one tiny passage in the foreword changed my outlook on something important. Here it is:
Sometime during my childhood I encountered the traditional image of a bird that erodes a mountain by taking a single stone from it every year.</description></item><item><title>An Amazon Story</title><link>https://zhubert.com/writing/an-amazon-story/</link><pubDate>Fri, 18 Apr 2014 00:00:00 +0000</pubDate><guid>https://zhubert.com/writing/an-amazon-story/</guid><description>This last week I was sitting with friends around a campfire and told the following true story. They found it rather interesting, so I figured it was worth retelling. The truth is, my career has been a really weird one…there’s nothing linear about any of the progression through work that I’ve chosen. It has been a truly wild ride, but I’m getting ahead of myself.
Amazon. 1999. It was a totally different company than it is now, though in many ways it’s probably still Day 1.</description></item></channel></rss>