<?xml version="1.0" encoding="utf-8"?>
<oembed>
  <version>1</version>
  <type>rich</type>
  <provider_name>Libsyn</provider_name>
  <provider_url>https://www.libsyn.com</provider_url>
  <height>90</height>
  <width>600</width>
  <title>36 - Adam Shai and Paul Riechers on Computational Mechanics</title>
  <description>Sometimes, people talk about transformers as having &amp;quot;world models&amp;quot; as a result of being trained to predict text data on the internet. But what does this even mean? In this episode, I talk with Adam Shai and Paul Riechers about their work applying computational mechanics, a sub-field of physics studying how to predict random processes, to neural networks. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast The transcript:  https://axrp.net/episode/2024/09/29/episode-36-adam-shai-paul-riechers-computational-mechanics.html &amp;amp;nbsp; Topics we discuss, and timestamps: 0:00:42 - What computational mechanics is 0:29:49 - Computational mechanics vs other approaches 0:36:16 - What world models are 0:48:41 - Fractals 0:57:43 - How the fractals are formed 1:09:55 - Scaling computational mechanics for transformers 1:21:52 - How Adam and Paul found computational mechanics 1:36:16 - Computational mechanics for AI safety 1:46:05 - Following Adam and Paul's research &amp;amp;nbsp; Simplex AI Safety: https://www.simplexaisafety.com/ &amp;amp;nbsp; Research we discuss: Transformers represent belief state geometry in their residual stream: https://arxiv.org/abs/2405.15943 Transformers represent belief state geometry in their residual stream [LessWrong post]:  https://www.lesswrong.com/posts/gTZ2SxesbHckJ3CkF/transformers-represent-belief-state-geometry-in-their Why Would Belief-States Have A Fractal Structure, And Why Would That Matter For Interpretability? An Explainer:  https://www.lesswrong.com/posts/mBw7nc4ipdyeeEpWs/why-would-belief-states-have-a-fractal-structure-and-why &amp;amp;nbsp; Episode art by Hamish Doodles:&amp;amp;nbsp;hamishdoodles.com </description>
  <author_name>AXRP - the AI X-risk Research Podcast</author_name>
  <author_url>https://axrp.net</author_url>
  <html>&lt;iframe title="Libsyn Player" style="border: none" src="//html5-player.libsyn.com/embed/episode/id/33247517/height/90/theme/custom/thumbnail/yes/direction/forward/render-playlist/no/custom-color/88AA3C/" height="90" width="600" scrolling="no"  allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen&gt;&lt;/iframe&gt;</html>
  <thumbnail_url>https://assets.libsyn.com/secure/content/178812522</thumbnail_url>
</oembed>
