<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>Jack Koch</title>
      <link>https://jbkjr.me</link>
      <description>Last 10 notes on Jack Koch</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>A Dhamma Glossary</title>
    <link>https://jbkjr.me/dhamma/glossary</link>
    <guid>https://jbkjr.me/dhamma/glossary</guid>
    <description><![CDATA[ A historical-stratum reference for the dhamma, in order to understand the goal and how to attain it. ]]></description>
    <pubDate>Sat, 12 Sep 2026 17:25:02 GMT</pubDate>
  </item><item>
    <title>dhamma</title>
    <link>https://jbkjr.me/dhamma/</link>
    <guid>https://jbkjr.me/dhamma/</guid>
    <description><![CDATA[ Notes, references, and writings on the dhamma — beginning with a historical-stratum glossary of Pāli, Sanskrit, and comparative terminology. ]]></description>
    <pubDate>Sat, 25 Apr 2026 21:14:15 GMT</pubDate>
  </item><item>
    <title>Goal Misgeneralization</title>
    <link>https://jbkjr.me/projects/goal-misgeneralization</link>
    <guid>https://jbkjr.me/projects/goal-misgeneralization</guid>
    <description><![CDATA[ I co-led this research project at the AI Safety Camp, producing the first empirical demonstrations of goal misgeneralization in deep reinforcement learning. ]]></description>
    <pubDate>Thu, 30 Oct 2025 17:52:21 GMT</pubDate>
  </item><item>
    <title>Understanding Agency</title>
    <link>https://jbkjr.me/projects/understanding-agency</link>
    <guid>https://jbkjr.me/projects/understanding-agency</guid>
    <description><![CDATA[ During a summer fellowship at the Center on Long-term Risk, I investigated how philosophical and neuroscientific perspectives on agency could inform AI safety research. ]]></description>
    <pubDate>Thu, 30 Oct 2025 17:52:21 GMT</pubDate>
  </item><item>
    <title>About</title>
    <link>https://jbkjr.me/</link>
    <guid>https://jbkjr.me/</guid>
    <description><![CDATA[ I graduated from Yale with a B.S. in Applied Mathematics and a concentration in Computer Science in May 2019. ]]></description>
    <pubDate>Thu, 30 Oct 2025 17:46:37 GMT</pubDate>
  </item><item>
    <title>Suffering Is Not Pain</title>
    <link>https://jbkjr.me/posts/suffering-is-not-pain</link>
    <guid>https://jbkjr.me/posts/suffering-is-not-pain</guid>
    <description><![CDATA[ “Pain is inevitable; suffering is optional.” The motivation of this post is to address the persistent conflation between suffering and pain I have observed from members of the EA community, even amongst those who purport to be “suffering-focused” in their ethical motivations. ]]></description>
    <pubDate>Tue, 18 Jun 2024 00:00:00 GMT</pubDate>
  </item><item>
    <title>Why I stopped working on AI safety</title>
    <link>https://jbkjr.me/posts/why-i-am-no-longer-ai-safety</link>
    <guid>https://jbkjr.me/posts/why-i-am-no-longer-ai-safety</guid>
    <description><![CDATA[ Here’s a description of a future which I understand Rationalists and Effective Altruists in general would endorse as an (if not the) ideal outcome of the labors of humanity: no suffering, minimal pain/displeasure, maximal ‘happiness’ (preferably for an astronomical number of intelligent, sentient mi... ]]></description>
    <pubDate>Thu, 02 May 2024 00:00:00 GMT</pubDate>
  </item><item>
    <title>Mapping the Conceptual Territory in AI Existential Safety and Alignment</title>
    <link>https://jbkjr.me/posts/mapping-conceptual-territory</link>
    <guid>https://jbkjr.me/posts/mapping-conceptual-territory</guid>
    <description><![CDATA[ Throughout my studies in alignment and AI-related existential risks, I’ve found it helpful to build a mental map of the field and how its various questions and considerations interrelate, so that when I read a new paper, a post on the Alignment Forum, or similar material, I have some idea of how it ... ]]></description>
    <pubDate>Thu, 17 Dec 2020 00:00:00 GMT</pubDate>
  </item><item>
    <title>Spinning Up in Deep RL: Getting Started</title>
    <link>https://jbkjr.me/posts/getting-started-spinning-up</link>
    <guid>https://jbkjr.me/posts/getting-started-spinning-up</guid>
    <description><![CDATA[ I’ll be spending the next month getting some hands-on experience with deep reinforcement learning via OpenAI’s Spinning Up in Deep RL, which includes both an overview of key concepts in deep reinforcement learning and a well-documented repository of implementations of key algorithms that are designe... ]]></description>
    <pubDate>Sun, 29 Nov 2020 00:00:00 GMT</pubDate>
  </item><item>
    <title>The Need for Better Terminology in Discussing Existential Risks from AI</title>
    <link>https://jbkjr.me/posts/better-x-risk-terminology</link>
    <guid>https://jbkjr.me/posts/better-x-risk-terminology</guid>
    <description><![CDATA[ Recently, I listened to a podcast1 from the Future of Life Institute in which Andrew Critch (from the Center for Human Compatible AI at Berkeley) discussed his and David Krueger’s recent paper, “AI Research Considerations for Human Existential Safety (ARCHES)”2. ]]></description>
    <pubDate>Thu, 08 Oct 2020 00:00:00 GMT</pubDate>
  </item>
    </channel>
  </rss>