<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Gpt on csegura</title><link>https://blog.romheat.net/tags/gpt/</link><description>Recent content in Gpt on csegura</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 16 Aug 2023 00:00:00 +0100</lastBuildDate><atom:link href="https://blog.romheat.net/tags/gpt/index.xml" rel="self" type="application/rss+xml"/><item><title>GPT News anonymizer</title><link>https://blog.romheat.net/posts/2023/23_08_16_gpt_model_explorer/</link><pubDate>Wed, 16 Aug 2023 00:00:00 +0100</pubDate><guid>https://blog.romheat.net/posts/2023/23_08_16_gpt_model_explorer/</guid><description>&lt;p>I&amp;rsquo;m using at home my own server to run gpt models. Without cost I can do funny and stupid things. This one run a pipeline of tasks to anonymize news, critics, sumarize, extract names, places, products, etc.&lt;/p>
&lt;p>First I get the entries from google trends&lt;/p>
&lt;p>&lt;img src="https://blog.romheat.net/images/misc/gpt_extractor.png" alt="">&lt;/p>
&lt;p>Then I use the GPT model to generate the news.&lt;/p>
&lt;p>With this I can generate my own &amp;ldquo;News Corporation&amp;rdquo;&lt;/p>
&lt;p>The pipeline is like this:&lt;/p></description></item></channel></rss>