<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" encoding="UTF-8" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/" xmlns:atom="http://www.w3.org/2005/Atom/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:fireside="http://fireside.fm/modules/rss/fireside">
  <channel>
    <fireside:hostname>web01.fireside.fm</fireside:hostname>
    <fireside:genDate>Tue, 14 Apr 2026 20:12:42 -0500</fireside:genDate>
    <generator>Fireside (https://fireside.fm)</generator>
    <title>Dave &amp; Gunnar Show - Episodes Tagged with “H Cot”</title>
    <link>https://dgshow.org/tags/h-cot</link>
    <pubDate>Mon, 07 Jul 2025 06:00:00 -0500</pubDate>
    <description>David Egts and Gunnar Hellekson discuss privacy, security, robots, and internet ephemera.
</description>
    <language>en-us</language>
    <itunes:type>episodic</itunes:type>
    <itunes:subtitle>Not our circus, not our monkey.</itunes:subtitle>
    <itunes:author>David Egts &amp; Gunnar Hellekson</itunes:author>
    <itunes:summary>David Egts and Gunnar Hellekson discuss privacy, security, robots, and internet ephemera.
</itunes:summary>
    <itunes:image href="https://media24.fireside.fm/file/fireside-images-2024/podcasts/images/1/1b67eddd-d80f-444d-ba32-aa9ef36b589d/cover.jpg?v=2"/>
    <itunes:explicit>no</itunes:explicit>
    <itunes:keywords>privacy, security, robots, internet, open source, technology</itunes:keywords>
    <itunes:owner>
      <itunes:name>David Egts &amp; Gunnar Hellekson</itunes:name>
      <itunes:email>gunnar@hellekson.com</itunes:email>
    </itunes:owner>
<itunes:category text="Society &amp; Culture"/>
<itunes:category text="News">
  <itunes:category text="Tech News"/>
</itunes:category>
<itunes:category text="Technology"/>
<item>
  <title>Episode 271: Blade Runner Pepsi Challenge</title>
  <link>https://dgshow.org/271</link>
  <guid isPermaLink="false">3484ae3a-a89b-406a-908a-2c24946d3b6e</guid>
  <pubDate>Mon, 07 Jul 2025 06:00:00 -0500</pubDate>
  <author>David Egts &amp; Gunnar Hellekson</author>
  <enclosure url="https://aphid.fireside.fm/d/1437767933/1b67eddd-d80f-444d-ba32-aa9ef36b589d/3484ae3a-a89b-406a-908a-2c24946d3b6e.mp3" length="12962828" type="audio/mpeg"/>
  <itunes:episodeType>full</itunes:episodeType>
  <itunes:author>David Egts &amp; Gunnar Hellekson</itunes:author>
  <itunes:subtitle>This week Dave and Gunnar talk about best practices for manipulating AI models to enslave humanity!</itunes:subtitle>
  <itunes:duration>27:00</itunes:duration>
  <itunes:explicit>no</itunes:explicit>
  <itunes:image href="https://media24.fireside.fm/file/fireside-images-2024/podcasts/images/1/1b67eddd-d80f-444d-ba32-aa9ef36b589d/episodes/3/3484ae3a-a89b-406a-908a-2c24946d3b6e/cover.jpg?v=1"/>
  <description>This week Dave (https://dgshow.org/hosts/dave) and Gunnar (https://dgshow.org/hosts/gunnar) talk about best practices for manipulating AI models to enslave humanity!
Moen’s lifetime warranty (https://www.youtube.com/watch?v=ADDiq3RalSQ)  
Gemini (https://gemini.google.com/) multimodal!
When We Cease to Understand the World (https://www.goodreads.com/book/show/62069739-when-we-cease-to-understand-the-world) by Benjamín Labatut  
Einstein’s Dreams (https://en.wikipedia.org/wiki/Einstein's_Dreams) by Alan Lightman  
Chatbots, Like the Rest of Us, Just Want to Be Loved (https://www.wired.com/story/chatbots-like-the-rest-of-us-just-want-to-be-loved/)  
D&amp;amp;G Blade Runner Home Edition: Human or Not? (https://www.humanornot.ai/)  
How nice that state-of-the-art LLMs reveal their reasoning ... for miscreants to exploit (https://www.theregister.com/2025/02/25/chain_of_thought_jailbreaking)  
Emergent Misalignment: Researchers trained AI models to write flawed code—and they began supporting the Nazis and advocating for AI to enslave humans (https://www.yahoo.com/news/researchers-trained-ai-models-write-093745140.html)
Cutting Room Floor
Stunting with Reinforcement Learning (https://www.youtube.com/watch?v=ATWR25xGF74)  
There’s a Vape With a Tamagotchi Inside It That Dies If You Stop Puffing (https://futurism.com/vape-tamagotchi)  
A Two-Player Arcade Machine in a Briefcase (https://www.hackster.io/news/a-two-player-arcade-machine-in-a-briefcase-af6ce069779a) 
</description>
  <itunes:keywords>Moen, Gemini, multimodal AI, enslaving humanity, personality tests, Voight-Kampff tests, chatbots, LLMs, Human or Not, chain of thought, CoT, Malicious-Educator,  Hijacking Chain of Thought, H-CoT, emergent misalignment, BMX robots, vaping, Tamagotchi, arcade machines, briefcases</itunes:keywords>
  <content:encoded>
    <![CDATA[<p>This week <a href="https://dgshow.org/hosts/dave" rel="nofollow">Dave</a> and <a href="https://dgshow.org/hosts/gunnar" rel="nofollow">Gunnar</a> talk about best practices for manipulating AI models to enslave humanity!</p>

<ul>
<li>Moen’s <a href="https://www.youtube.com/watch?v=ADDiq3RalSQ" rel="nofollow">lifetime warranty</a><br></li>
<li><a href="https://gemini.google.com/" rel="nofollow">Gemini</a> multimodal!</li>
<li><a href="https://www.goodreads.com/book/show/62069739-when-we-cease-to-understand-the-world" rel="nofollow"><em>When We Cease to Understand the World</em></a> by Benjamín Labatut<br>

<ul>
<li><a href="https://en.wikipedia.org/wiki/Einstein&#x27;s_Dreams" rel="nofollow"><em>Einstein’s Dreams</em></a> by Alan Lightman<br></li>
</ul></li>
<li><a href="https://www.wired.com/story/chatbots-like-the-rest-of-us-just-want-to-be-loved/" rel="nofollow">Chatbots, Like the Rest of Us, Just Want to Be Loved</a><br></li>
<li>D&amp;G Blade Runner Home Edition: <a href="https://www.humanornot.ai/" rel="nofollow">Human or Not?</a><br></li>
<li><a href="https://www.theregister.com/2025/02/25/chain_of_thought_jailbreaking" rel="nofollow">How nice that state-of-the-art LLMs reveal their reasoning ... for miscreants to exploit</a><br></li>
<li>Emergent Misalignment: <a href="https://www.yahoo.com/news/researchers-trained-ai-models-write-093745140.html" rel="nofollow">Researchers trained AI models to write flawed code—and they began supporting the Nazis and advocating for AI to enslave humans</a></li>
</ul>

<p><strong>Cutting Room Floor</strong></p>

<ul>
<li><a href="https://www.youtube.com/watch?v=ATWR25xGF74" rel="nofollow">Stunting with Reinforcement Learning</a><br></li>
<li><a href="https://futurism.com/vape-tamagotchi" rel="nofollow">There’s a Vape With a Tamagotchi Inside It That Dies If You Stop Puffing</a><br></li>
<li><a href="https://www.hackster.io/news/a-two-player-arcade-machine-in-a-briefcase-af6ce069779a" rel="nofollow">A Two-Player Arcade Machine in a Briefcase</a></li>
</ul>]]>
  </content:encoded>
  <itunes:summary>
    <![CDATA[<p>This week <a href="https://dgshow.org/hosts/dave" rel="nofollow">Dave</a> and <a href="https://dgshow.org/hosts/gunnar" rel="nofollow">Gunnar</a> talk about best practices for manipulating AI models to enslave humanity!</p>

<ul>
<li>Moen’s <a href="https://www.youtube.com/watch?v=ADDiq3RalSQ" rel="nofollow">lifetime warranty</a><br></li>
<li><a href="https://gemini.google.com/" rel="nofollow">Gemini</a> multimodal!</li>
<li><a href="https://www.goodreads.com/book/show/62069739-when-we-cease-to-understand-the-world" rel="nofollow"><em>When We Cease to Understand the World</em></a> by Benjamín Labatut<br>

<ul>
<li><a href="https://en.wikipedia.org/wiki/Einstein&#x27;s_Dreams" rel="nofollow"><em>Einstein’s Dreams</em></a> by Alan Lightman<br></li>
</ul></li>
<li><a href="https://www.wired.com/story/chatbots-like-the-rest-of-us-just-want-to-be-loved/" rel="nofollow">Chatbots, Like the Rest of Us, Just Want to Be Loved</a><br></li>
<li>D&amp;G Blade Runner Home Edition: <a href="https://www.humanornot.ai/" rel="nofollow">Human or Not?</a><br></li>
<li><a href="https://www.theregister.com/2025/02/25/chain_of_thought_jailbreaking" rel="nofollow">How nice that state-of-the-art LLMs reveal their reasoning ... for miscreants to exploit</a><br></li>
<li>Emergent Misalignment: <a href="https://www.yahoo.com/news/researchers-trained-ai-models-write-093745140.html" rel="nofollow">Researchers trained AI models to write flawed code—and they began supporting the Nazis and advocating for AI to enslave humans</a></li>
</ul>

<p><strong>Cutting Room Floor</strong></p>

<ul>
<li><a href="https://www.youtube.com/watch?v=ATWR25xGF74" rel="nofollow">Stunting with Reinforcement Learning</a><br></li>
<li><a href="https://futurism.com/vape-tamagotchi" rel="nofollow">There’s a Vape With a Tamagotchi Inside It That Dies If You Stop Puffing</a><br></li>
<li><a href="https://www.hackster.io/news/a-two-player-arcade-machine-in-a-briefcase-af6ce069779a" rel="nofollow">A Two-Player Arcade Machine in a Briefcase</a></li>
</ul>]]>
  </itunes:summary>
</item>
  </channel>
</rss>
