<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>interactive on Coding in Space</title><link>https://ceres1.space/tags/interactive/</link><description>Recent content in interactive on Coding in Space</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Josh Leverette</copyright><lastBuildDate>Wed, 05 Aug 2026 19:33:03 -0500</lastBuildDate><atom:link href="https://ceres1.space/tags/interactive/index.xml" rel="self" type="application/rss+xml"/><item><title>LLMs, from the Beginning — Part 1: The Next Token</title><link>https://ceres1.space/posts/llms-from-the-beginning/the-next-token/</link><pubDate>Wed, 05 Aug 2026 19:33:03 -0500</pubDate><guid>https://ceres1.space/posts/llms-from-the-beginning/the-next-token/</guid><description>See how next-token completion becomes few-shot prompting, chat, tool use, and reasoning through interactive, token-level exhibits.</description></item><item><title>LLMs, from the Beginning — Part 2: Remembering the Prompt</title><link>https://ceres1.space/posts/llms-from-the-beginning/remembering-the-prompt/</link><pubDate>Wed, 05 Aug 2026 19:33:02 -0500</pubDate><guid>https://ceres1.space/posts/llms-from-the-beginning/remembering-the-prompt/</guid><description>Open the KV cache, count what every remembered token costs, and explore how modern attention designs handle long context.</description></item><item><title>LLMs, from the Beginning — Part 3: Breaking the One-Token Barrier</title><link>https://ceres1.space/posts/llms-from-the-beginning/breaking-the-one-token-barrier/</link><pubDate>Wed, 05 Aug 2026 19:33:01 -0500</pubDate><guid>https://ceres1.space/posts/llms-from-the-beginning/breaking-the-one-token-barrier/</guid><description>Connect arithmetic intensity, continuous batching, sparse experts, and speculative decoding to the latency each user feels.</description></item></channel></rss>