<?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>Sft on knowledged.to</title><link>https://knowledged.to/tags/sft/</link><description>Recent content in Sft on knowledged.to</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 24 Jun 2026 05:59:20 +0000</lastBuildDate><atom:link href="https://knowledged.to/tags/sft/index.xml" rel="self" type="application/rss+xml"/><item><title>Where RL Fits: Training vs. Inference in the LLM Pipeline</title><link>https://knowledged.to/ai/concepts/where-rl-fits-training-vs-inference-llm-pipeline/</link><pubDate>Wed, 24 Jun 2026 05:43:38 +0000</pubDate><guid>https://knowledged.to/ai/concepts/where-rl-fits-training-vs-inference-llm-pipeline/</guid><description>Explains that RL in LLMs is a training/alignment stage, not inference, with pipeline context.</description></item></channel></rss>