<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Architecture on Hitesh Pattanayak</title><link>/tags/architecture/</link><description>Recent content in Architecture on Hitesh Pattanayak</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 22 Mar 2026 11:43:37 -0700</lastBuildDate><atom:link href="/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>The Evolution: Beyond Transformers</title><link>/posts/the-evolution-beyond-transformers/</link><pubDate>Sun, 22 Mar 2026 11:43:37 -0700</pubDate><guid>/posts/the-evolution-beyond-transformers/</guid><description>A practical walkthrough of how the Transformer architecture evolved from encoder-decoder to decoder-only models, why attention&amp;rsquo;s quadratic scaling became a hard wall, and how Mamba&amp;rsquo;s state space machines are being absorbed into hybrid architectures that dominate production today.</description></item><item><title>Inside the Machine: Encoders, Decoders, and Masking</title><link>/posts/inside-the-machine-encoders-decoders-and-masking/</link><pubDate>Sat, 21 Mar 2026 12:19:38 -0700</pubDate><guid>/posts/inside-the-machine-encoders-decoders-and-masking/</guid><description>A practical deep-dive into how the Transformer&amp;rsquo;s encoder and decoder stacks work, covering residual connections, positional encoding, masked self-attention, and cross-attention with code examples throughout.</description></item></channel></rss>