<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tau on</title><link>/tags/tau/</link><description>Recent content in Tau on</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 29 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="/tags/tau/index.xml" rel="self" type="application/rss+xml"/><item><title>Week 26, 2026</title><link>/weekly/2026-w26/</link><pubDate>Mon, 29 Jun 2026 00:00:00 +0000</pubDate><guid>/weekly/2026-w26/</guid><description>&lt;p>June 29 — July 5, 2026&lt;/p>
&lt;h2 class="heading" id="this-week">
 This week
 &lt;a href="#this-week">#&lt;/a>
&lt;/h2>
&lt;ul>
&lt;li>Revived this site as a public record of a 6-month research engineering trajectory.&lt;/li>
&lt;li>Settled on a structure: transformers + LLM inference + efficient kernels as the core trunk; agents, SOTA papers, and TypeScript literacy as satellites.&lt;/li>
&lt;li>Blocked study time on the calendar for the next 8 weeks.&lt;/li>
&lt;li>Started a living note to track direction: &lt;a href="/projects/research-engineer-trajectory/">Research Engineer Trajectory&lt;/a>.&lt;/li>
&lt;/ul>
&lt;h2 class="heading" id="up-next">
 Up next
 &lt;a href="#up-next">#&lt;/a>
&lt;/h2>
&lt;ul>
&lt;li>Read the Word2Vec paper and understand CBOW / skip-gram / negative sampling.&lt;/li>
&lt;li>Implement Word2Vec from scratch in NumPy or raw PyTorch.&lt;/li>
&lt;li>Explore &lt;a href="https://github.com/huggingface/tau">Tau&lt;/a> as a Python agent harness for MVF work.&lt;/li>
&lt;/ul>
&lt;h2 class="heading" id="open-questions">
 Open questions
 &lt;a href="#open-questions">#&lt;/a>
&lt;/h2>
&lt;ul>
&lt;li>What part of the transformer/inference stack lights me up most as I go deeper?&lt;/li>
&lt;li>How much focused work can I realistically get from the 3–7pm weekday blocks?&lt;/li>
&lt;/ul></description></item></channel></rss>