<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Local on The Augmented Scholar</title><link>https://augmentedscholars.com/tags/local/</link><description>Recent content in Local on The Augmented Scholar</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 18 Jul 2026 16:33:26 +0400</lastBuildDate><atom:link href="https://augmentedscholars.com/tags/local/index.xml" rel="self" type="application/rss+xml"/><item><title>Ollama — Local LLMs in One Command</title><link>https://augmentedscholars.com/tools/ollama/</link><pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate><guid>https://augmentedscholars.com/tools/ollama/</guid><description>&lt;h2 id="overview"&gt;Overview&lt;/h2&gt;
&lt;p&gt;Ollama makes local LLMs boring in the best way: &amp;lsquo;ollama run llama3.3&amp;rsquo; downloads and serves a model on your machine, with an OpenAI-compatible API for scripts. For research on sensitive data — interviews, patient text, embargoed drafts — it is the only AI assistance that never leaves the room.&lt;/p&gt;</description></item><item><title>Whisper — Open-Source Transcription That Ended an Industry</title><link>https://augmentedscholars.com/tools/whisper/</link><pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate><guid>https://augmentedscholars.com/tools/whisper/</guid><description>&lt;h2 id="overview"&gt;Overview&lt;/h2&gt;
&lt;p&gt;Whisper transcribes speech to text with near-human accuracy across accents, noise, and 100 languages — and because the weights are open, it runs entirely on your machine. For interview-based research, it converted a per-hour-billed service industry into a local batch job with zero confidentiality exposure.&lt;/p&gt;</description></item></channel></rss>