<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Ai on MoskitoHero</title><link>/tags/ai/</link><description>Recent content in Ai on MoskitoHero</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 03 Jun 2026 12:24:12 +0200</lastBuildDate><atom:link href="/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>I Am Not a Robot</title><link>/post/i-am-not-a-robot/</link><pubDate>Wed, 03 Jun 2026 12:24:12 +0200</pubDate><guid>/post/i-am-not-a-robot/</guid><description>I have a confession to make: I am not a robot. Should I let my coding style be dictated by the fear of sounding like one? I don’t think so.</description><content:encoded><![CDATA[<div class="paragraph">
<p>I have a confession to make: <em>I am not a robot</em>.</p>
</div>
<div class="paragraph">
<p>But lately, I must admit I felt the urge to make sure I did not read like one. Let me explain:</p>
</div>
<div class="paragraph">
<p>I am the kind of developer who loves clean code and knows the <a href="https://www.poodr.com/">POODR book</a> by heart in 7 languages (I don’t, but you get the idea). I always thoroughly document my code with Yard. I stick to TDD as much as I can. I try to write extensive commit messages and PR descriptions.</p>
</div>
<div class="paragraph">
<p>On the other hand, I love to try new, shiny things. I change patterns when I feel like it (my latest <em>personal coding-style hype</em> was inlining <code>private</code> keywords in ruby method definitions). My tests never look exactly the same. I am, in some ways, inconsistent.</p>
</div>
<div class="paragraph">
<p>When I code, I often go the extra mile and refactor stuff along the way, which makes my PRs a little fatter and less laser-focused than they should.</p>
</div>
<div class="paragraph">
<p>But lately, as I was writing a very detailed commit message, with lots of bullet points and em-dashes to make it extra-clear what my intent was, it occurred to me that all of these made me sound like a LLM. In fact, the whole thing I was about to ship could appear as vibe-coded — it was not.</p>
</div>
<div class="paragraph">
<p>What will the reviewers think of my work? What will they think of me? A vibe coder? No way.</p>
</div>
<div class="paragraph">
<p>Let me get this straight: I do use AI. But it is my pair programmer, my assistant, my rubber duck, my intern — with one caveat: I have to make my own coffee.</p>
</div>
<div class="paragraph">
<p>I am in charge. I code. I write tests.</p>
</div>
<div class="paragraph">
<p>So, for a moment, as I was proof-reading that commit message, I was tempted to add a few inconsistencies, remove the em-dashes and keep a few typos…​</p>
</div>
<div class="paragraph">
<p>I didn’t.</p>
</div>
<div class="paragraph">
<p>Screw it, I am not a robot.</p>
</div>
]]></content:encoded></item><item><title>Opening the Mind of a Thinking Agent</title><link>/post/2026-05-12-opening-the-mind-of-a-thinking-agent/</link><pubDate>Tue, 12 May 2026 22:10:00 +0000</pubDate><guid>/post/2026-05-12-opening-the-mind-of-a-thinking-agent/</guid><description>Reflecting on my experience of using AI agents for coding, I start wondering what is really hiding behind the concept of a &amp;#34;thinking agent&amp;#34;. Time to take a look inside its brain…​</description><content:encoded><![CDATA[<div class="paragraph">
<p>My brain is a dumpster tonight.</p>
</div>
<div class="paragraph">
<p>I kind of felt lazy all day, so I decided to rely on agents to leverage most of the work I had to do. The result is that I now feel totally depressed and tired. Everything was wrong with that day’s work.</p>
</div>
<div class="paragraph">
<p>It was tempting, at first. I thought I would have AI do the boring bits, type less on my keyboard and become an orchestrator. I thought it would give me more control over my priorities and help me dash through the day like a warrior, like a knight proudly riding his horse.</p>
</div>
<div class="paragraph">
<p>Now it’s 6 p.m. It feels like the horse has been trampling on my back all afternoon and is now chewing on my hair.</p>
</div>
<div class="paragraph">
<p>What did I get from today’s coding session? I remember giving instructions to the agent. I remember waiting for it to reply. I remember being unsatisfied with what it proposed as a solution. I remember guiding him step by step through the process. I remember looking at the screen in disbelief as it took five minutes to move a piece of code from one file to another.</p>
</div>
<div class="paragraph">
<p>I could have done it in seconds. Still, I was kind of relieved not to do the boring chores.</p>
</div>
<div class="paragraph">
<p>Looking back, I feel that what really happened is that I switched off my brain and surrendered it to the Machine. Now I feel ashamed.</p>
</div>
<div class="paragraph">
<p>All that time the machine was thinking. I wasn’t.</p>
</div>
<div class="sect2">
<h3 id="thinking"><a class="anchor" href="#thinking"></a><em>Thinking…​</em></h3>
<div class="paragraph">
<p>That word intrigued me. So I clicked on it. A toggle opened. And man, was that ugly…​</p>
</div>
<div class="paragraph">
<p>What AI companies advertise as thinking is actually a computer program mumbling for ages, balancing ideas and their opposites, trying to figure out what exactly I meant, taking U-turns, battling against itself on details so insignificant it would drive anyone with a sane mind totally nuts. This is not thinking. This is vomiting words by the gallon. This is a brute-force parody of a french political debate.</p>
</div>
<div class="paragraph">
<p>My experience of thinking is not filling up pages and pages of words based on the likelihood of their occuring in a single sequence, and then taking these pages of writing to write yet another round of pages of nonsense until I decide I am confident enough to tell you I have finished thinking.</p>
</div>
<div class="paragraph">
<p>My experience of thinking actually implies growing up as a person and as a professional, backed by an intimate network of neurons I have patiently connected throughout the years by the means of experience, reading, learning, meeting, confronting ideas.</p>
</div>
<div class="paragraph">
<p>My experience of thinking is tied to the dose of dopamine I get when, Eureka! I finally found the solution. I didn’t get my fix today. I gave it up to Claude, who took five long minutes of water-heating, climate-warming and deforesting to spit out an unconvincing solution while I looked bluntly at my screen like a Half-Life zombie crying out for brain.</p>
</div>
<div class="literalblock">
<div class="content">
<pre>🧟‍♂️🧟‍♂️🧟‍♂️ Braaaaaiiiin... 🧠🧠🧠</pre>
</div>
</div>
<div class="paragraph">
<p>Luckily enough, I got woken up by a message telling me I had reached my daily quota. That’s when I realized the pain and frustration I had been inflicting myself.</p>
</div>
<div class="paragraph">
<p>Thinking is a pleasure. I will not let a machine with no feelings take it away from me.</p>
</div>
</div>
<div class="sect2">
<h3 id="lets-wrap-it-up"><a class="anchor" href="#lets-wrap-it-up"></a>Let’s wrap it up.</h3>
<div class="paragraph">
<p>I am not anti-AI. That would be stupid. Like being anti-electricity, or anti-dishwasher, or anti-railway. I just want to keep my agent saddled-up tight underneath me like a faithful horse I can control. I want to <strong>use</strong> AI, and never let it be the other way round.</p>
</div>
<div class="paragraph">
<p>I feel it is time to review my AI deontology. This is the plan:</p>
</div>
<hr/>
<div class="ulist">
<ul>
<li>
<p>Remove uneeded CLI agents I have installed just &#34;to try it out&#34;.</p>
</li>
<li>
<p>Remove IDE plugins, extensions, apart from code completion stuff. That is often useful.</p>
</li>
<li>
<p>In Zed, check &#34;disable AI&#34;</p>
</li>
<li>
<p>Keep Claude Code (company subscription) installed — Claude  desktop was already uninstalled a long time ago — and stick to these rules:</p>
<div class="ulist">
<ul>
<li>
<p>Only reviews and ideation</p>
</li>
<li>
<p>No thinking models</p>
</li>
<li>
<p>No write access to anything whatsoever. Yes, even elisp.</p>
</li>
</ul>
</div>
</li>
</ul>
</div>
<hr/>
<div class="paragraph">
<p>And for the rest, I will stick to good old Organic Intelligence.</p>
</div>
</div>
]]></content:encoded></item></channel></rss>