<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Trust on Fernando Ruiz</title><link>https://www.fernandoux.com/tags/trust/</link><description>Recent content in Trust on Fernando Ruiz</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://www.fernandoux.com/tags/trust/index.xml" rel="self" type="application/rss+xml"/><item><title>Citations and sources in AI answers: how to show where each fact comes from</title><link>https://www.fernandoux.com/en/wiki/ai/citations-and-sources/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/en/wiki/ai/citations-and-sources/</guid><description>&lt;div class="info-panel"&gt;
 &lt;div class="info-header"&gt;
 &lt;span class="material-symbols-outlined info-panel-icon"&gt;info&lt;/span&gt;
 &lt;span class="info-panel-label"&gt;Quick Definition&lt;/span&gt;
 &lt;/div&gt;
 &lt;div class="info-content"&gt;
 A &lt;strong&gt;citation in an AI answer&lt;/strong&gt; is a reference that links a part of the text to the document, page or passage it comes from. It lets people check the claim at its origin, and it is only useful if the link points to a passage that actually supports it.
 &lt;/div&gt;
&lt;/div&gt;

&lt;h2 id="what-problem-do-citations-solve"&gt;What problem do citations solve?&lt;/h2&gt;
&lt;p&gt;A model can give a fluent, correct answer or a fluent, invented one, and both read the same. Without a reference, the person has to look up every fact on their own, and then the AI has not saved them any time. With a citation, verification costs one click.&lt;/p&gt;</description></item><item><title>How to show uncertainty in AI answers without confusing people</title><link>https://www.fernandoux.com/en/wiki/ai/showing-uncertainty/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/en/wiki/ai/showing-uncertainty/</guid><description>&lt;div class="info-panel"&gt;
 &lt;div class="info-header"&gt;
 &lt;span class="material-symbols-outlined info-panel-icon"&gt;info&lt;/span&gt;
 &lt;span class="info-panel-label"&gt;Quick Definition&lt;/span&gt;
 &lt;/div&gt;
 &lt;div class="info-content"&gt;
 &lt;strong&gt;Showing uncertainty&lt;/strong&gt; in an AI answer means communicating how sure the system is about what it says, which part is less reliable and how the person can check it. Done well, it helps people trust what is correct and doubt what is not; done badly, it is a disclaimer nobody reads.
 &lt;/div&gt;
&lt;/div&gt;

&lt;h2 id="why-should-a-model-say-it-is-not-sure"&gt;Why should a model say it is not sure?&lt;/h2&gt;
&lt;p&gt;A language model writes in the same tone whether it is right or making things up. The correct answer and the false one arrive with the same fluency, and the person has no signal to tell them apart. For a designer, that is the problem: the text carries no mark of its own quality.&lt;/p&gt;</description></item></channel></rss>