<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Transformers on mu0</title><link>https://mu0.ai/tags/transformers/</link><description>Recent content in Transformers on mu0</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Mon, 13 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://mu0.ai/tags/transformers/index.xml" rel="self" type="application/rss+xml"/><item><title>The Transformer Memory Architecture</title><link>https://mu0.ai/posts/transformer-memory-architecture/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://mu0.ai/posts/transformer-memory-architecture/</guid><description>Viewing transformers as long-term memory, working memory, and associative retrieval — and how Anthropic&amp;rsquo;s Workspace and J-Lens results fit into a memory-centric picture of the residual stream.</description></item><item><title>Transformer Blocks as Two Hopfield-Style Memory Systems</title><link>https://mu0.ai/posts/transformer-hopfield-memory/</link><pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate><guid>https://mu0.ai/posts/transformer-hopfield-memory/</guid><description>How attention mixes tokens via a modern Hopfield retrieval over context, while the MLP mixes channels via a Hopfield-like lookup into learned, persistent memories.</description></item></channel></rss>