<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tokens on Capsule One</title><link>https://capsule.one/tags/tokens/</link><description>Recent content in Tokens on Capsule One</description><generator>Hugo</generator><language>en-us</language><copyright>Capsule One B.V.</copyright><lastBuildDate>Thu, 16 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://capsule.one/tags/tokens/index.xml" rel="self" type="application/rss+xml"/><item><title>Why AI writes so much</title><link>https://capsule.one/mindscape/why-ai-writes-so-much/</link><pubDate>Thu, 16 Jul 2026 00:00:00 +0000</pubDate><guid>https://capsule.one/mindscape/why-ai-writes-so-much/</guid><description>&lt;p&gt;Lately i find myself constantly tweaking every aspect of my AI usage to “not write so much”.&lt;/p&gt;&#10;&lt;p&gt;Everything is so verbose everywhere. The conversation itself, commits, PR’s, comments in the code! Agents be writing so much unnecessary or wrongly placed detail.&lt;/p&gt;&#10;&lt;p&gt;I seriously wonder if this is not a tactic to just bloat token usage overall, which benefits AI model providers&lt;/p&gt;&#10;&lt;hr&gt;&#10;&lt;p&gt;&lt;em&gt;Originally posted on &lt;a href="https://x.com/RCM7/status/2077861303469981784"&gt;X&lt;/a&gt;&lt;/em&gt;&lt;/p&gt;</description></item></channel></rss>