<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Nutrition - Tag - vo.rs</title><link>https://vo.rs/tags/nutrition/</link><description>Nutrition - Tag - vo.rs</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright><lastBuildDate>Wed, 09 Jun 2021 16:28:00 +0000</lastBuildDate><atom:link href="https://vo.rs/tags/nutrition/" rel="self" type="application/rss+xml"/><item><title>Mediterranean Diet</title><link>https://vo.rs/story/mediterranean-diet/</link><description>&lt;p&gt;A confession about this page, because the honesty matters more than the tidiness. The article that used to sit here was generated by GPT-2, an early language model, as a deliberate experiment in machine-written text back in 2021. It read plausibly and it was almost entirely wrong — a smooth cascade of invented citations, garbled biochemistry, and confident nonsense about &amp;ldquo;meat-lover&amp;rsquo;s fries&amp;rdquo; and cancers of the &amp;ldquo;colon, colon, liver.&amp;rdquo; I&amp;rsquo;ve kept the URL and rewritten the substance from real sources, partly because the diet deserves an accurate write-up and partly because that old text is a perfect, preserved specimen of why you cannot trust fluent prose to be true prose. If you want the longer version of that lesson, I wrote about the practical limits of running your own models in &lt;a href="https://vo.rs/story/local-llms-a-practical-comparison-of-llama-mistral-and-gemma-for-real-work/" rel=""&gt;a comparison of Llama, Mistral and Gemma for real work&lt;/a&gt;; the short version is that a model&amp;rsquo;s confidence and a model&amp;rsquo;s correctness are entirely unrelated quantities. So here is the actual Mediterranean diet, with names, dates and studies you can check.&lt;/p&gt;</description><pubDate>Wed, 09 Jun 2021 16:28:00 +0000</pubDate></item></channel></rss>