<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet href="https://feeds.captivate.fm/style.xsl" type="text/xsl"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:podcast="https://podcastindex.org/namespace/1.0"><channel><atom:link href="https://feeds.captivate.fm/teach-us-something-new/" rel="self" type="application/rss+xml"/><title><![CDATA[Teach Us Something New]]></title><podcast:guid>2f102b90-0193-5bc1-aeba-0b2d7d3956b5</podcast:guid><lastBuildDate>Mon, 03 Aug 2026 15:58:25 +0000</lastBuildDate><generator>Captivate.fm</generator><language><![CDATA[en]]></language><copyright><![CDATA[Copyright 2026 Luke Hobson]]></copyright><managingEditor>Luke Hobson</managingEditor><itunes:summary><![CDATA[What happens when you sit down with some of the sharpest minds at MIT and ask them to teach you something? That's exactly what we find out on Teach Us Something New. Hosted by Dr. Luke Hobson, Head of Instructional Design at MIT xPRO, each episode dives deep into the expertise, research, and ideas that drive members of the MIT community. Whether you're a lifelong learner, an educator, or just genuinely curious, you're invited to learn something new alongside us. Teach Us Something New is proudly part of the MIT Learn Podcast Network.]]></itunes:summary><image><url>https://artwork.captivate.fm/f2db7950-e2d2-4c45-9aa3-c4727bf738e3/Teach-Us-Something-New-Graphic.jpg</url><title>Teach Us Something New</title><link><![CDATA[https://teach-us-something-new.captivate.fm]]></link></image><itunes:image href="https://artwork.captivate.fm/f2db7950-e2d2-4c45-9aa3-c4727bf738e3/Teach-Us-Something-New-Graphic.jpg"/><itunes:owner><itunes:name>Luke Hobson</itunes:name></itunes:owner><itunes:author>Luke Hobson</itunes:author><description>What happens when you sit down with some of the sharpest minds at MIT and ask them to teach you something? That&apos;s exactly what we find out on Teach Us Something New. Hosted by Dr. Luke Hobson, Head of Instructional Design at MIT xPRO, each episode dives deep into the expertise, research, and ideas that drive members of the MIT community. Whether you&apos;re a lifelong learner, an educator, or just genuinely curious, you&apos;re invited to learn something new alongside us. Teach Us Something New is proudly part of the MIT Learn Podcast Network.</description><link>https://teach-us-something-new.captivate.fm</link><atom:link href="https://pubsubhubbub.appspot.com" rel="hub"/><itunes:explicit>false</itunes:explicit><itunes:type>episodic</itunes:type><itunes:category text="Education"></itunes:category><itunes:category text="Education"><itunes:category text="Courses"/></itunes:category><itunes:category text="Education"><itunes:category text="How To"/></itunes:category><podcast:locked>no</podcast:locked><podcast:medium>podcast</podcast:medium><item><title>Harness Engineering with Jessica Cervi</title><itunes:title>Harness Engineering with Jessica Cervi</itunes:title><description><![CDATA[<p>In this episode, we sit down with <a href="https://www.linkedin.com/in/jessica-cervi/" rel="noopener noreferrer" target="_blank">Dr. Jessica Cervi</a>, a Learning Facilitator and Subject Matter Expert on AI for MIT xPRO. She'll walk us through harness engineering, an approach focused on building the environment an AI agent operates inside rather than just the instructions you hand it. Jessica breaks down how harness engineering differs from prompt and context engineering, why guardrails and evaluation are the two load-bearing pillars of the whole thing, and how using a more powerful model as a judge can catch the failures you would otherwise ship straight to your learners. We also dig into the tradeoff every builder runs into eventually: how much freedom to give an agent, and when the stakes of a task should pull you back toward tighter control. </p><p>Mentioned Links: </p><p><a href="https://xpro.mit.edu/courses/course-v1:xPRO+DAI/" rel="noopener noreferrer" target="_blank">Deploying AI for Strategic Impact</a></p><p><a href="https://www.faros.ai/blog/harness-engineering" rel="noopener noreferrer" target="_blank">Five Pillars</a></p>]]></description><content:encoded><![CDATA[<p>In this episode, we sit down with <a href="https://www.linkedin.com/in/jessica-cervi/" rel="noopener noreferrer" target="_blank">Dr. Jessica Cervi</a>, a Learning Facilitator and Subject Matter Expert on AI for MIT xPRO. She'll walk us through harness engineering, an approach focused on building the environment an AI agent operates inside rather than just the instructions you hand it. Jessica breaks down how harness engineering differs from prompt and context engineering, why guardrails and evaluation are the two load-bearing pillars of the whole thing, and how using a more powerful model as a judge can catch the failures you would otherwise ship straight to your learners. We also dig into the tradeoff every builder runs into eventually: how much freedom to give an agent, and when the stakes of a task should pull you back toward tighter control. </p><p>Mentioned Links: </p><p><a href="https://xpro.mit.edu/courses/course-v1:xPRO+DAI/" rel="noopener noreferrer" target="_blank">Deploying AI for Strategic Impact</a></p><p><a href="https://www.faros.ai/blog/harness-engineering" rel="noopener noreferrer" target="_blank">Five Pillars</a></p>]]></content:encoded><link><![CDATA[https://teach-us-something-new.captivate.fm]]></link><guid isPermaLink="false">90c0b79a-3955-42c5-ba00-a2986b9849e4</guid><itunes:image href="https://artwork.captivate.fm/f2db7950-e2d2-4c45-9aa3-c4727bf738e3/Teach-Us-Something-New-Graphic.jpg"/><pubDate>Mon, 03 Aug 2026 11:05:00 -0400</pubDate><enclosure url="https://episodes.captivate.fm/episode/90c0b79a-3955-42c5-ba00-a2986b9849e4.mp3" length="40723486" type="audio/mpeg"/><itunes:duration>28:11</itunes:duration><itunes:explicit>false</itunes:explicit><itunes:episodeType>full</itunes:episodeType><itunes:season>1</itunes:season><itunes:episode>2</itunes:episode><podcast:episode>2</podcast:episode><podcast:season>1</podcast:season><podcast:transcript url="https://transcripts.captivate.fm/transcript/0ef814ea-534e-44f4-ba59-681d8b908baf/index.html" type="text/html"/></item><item><title>Systems Thinking with Bruce Cameron</title><itunes:title>Systems Thinking with Bruce Cameron</itunes:title><description><![CDATA[<p>On today's episode, we're joined by <a href="https://systems.mit.edu/team/bruce-cameron/" rel="noopener noreferrer" target="_blank">Dr. Bruce Cameron</a>. He's the director of the <a href="https://systemarchitect.mit.edu" rel="noopener noreferrer" target="_blank">system architecture group</a>, a senior lecturer, and the faculty director for <a href="https://learn-xpro.mit.edu/systems-engineering?utm_term=systems%20engineering%20certificate&amp;utm_campaign=SysEngx-r28-search-leadgen&amp;utm_source=google&amp;utm_medium=ppc&amp;utm_content=run28-aw-usa-leadgen-phrase&amp;hsa_acc=2625711588&amp;hsa_cam=22653236069&amp;hsa_grp=184296172041&amp;hsa_ad=757014031665&amp;hsa_src=g&amp;hsa_tgt=kwd-330992309681&amp;hsa_kw=systems%20engineering%20certificate&amp;hsa_mt=p&amp;hsa_net=adwords&amp;hsa_ver=3&amp;gad_source=1&amp;gad_campaignid=22653236069&amp;gbraid=0AAAAADMFzx_P1p0Wk29IBsERkHt3RNsSC&amp;gclid=Cj0KCQjww8rQBhDjARIsAE43KPNwL3F05oSsk_zFPj4NWbLgBw9Iy5upCZ61CQininiAvvORKBh8-SEaAm_wEALw_wcB" rel="noopener noreferrer" target="_blank">MIT's Architecture and System Engineering Online Certificate Program</a>.</p><p>In this episode, we'll explore the world of systems thinking, what it really means to see the connections between events, why the decisions you make early in any complex system can determine everything that follows, and how organizations consistently undermine themselves by optimizing the wrong things. From NASA to Amazon to Meta, Bruce has seen systems succeed and fail at the highest levels, and he's here to share what he's learned, including some surprises along the way.</p><p><strong>Mentioned links:</strong></p><ul><li><a href="https://xpro.mit.edu/programs/program-v1:xPRO+SysEngx/" rel="noopener noreferrer" target="_blank">Architecture and Systems Engineering: Models and Methods to Manage Complex Systems</a></li><li><a href="https://learn.mit.edu" rel="noopener noreferrer" target="_blank">MIT Learn</a></li></ul><br/>]]></description><content:encoded><![CDATA[<p>On today's episode, we're joined by <a href="https://systems.mit.edu/team/bruce-cameron/" rel="noopener noreferrer" target="_blank">Dr. Bruce Cameron</a>. He's the director of the <a href="https://systemarchitect.mit.edu" rel="noopener noreferrer" target="_blank">system architecture group</a>, a senior lecturer, and the faculty director for <a href="https://learn-xpro.mit.edu/systems-engineering?utm_term=systems%20engineering%20certificate&amp;utm_campaign=SysEngx-r28-search-leadgen&amp;utm_source=google&amp;utm_medium=ppc&amp;utm_content=run28-aw-usa-leadgen-phrase&amp;hsa_acc=2625711588&amp;hsa_cam=22653236069&amp;hsa_grp=184296172041&amp;hsa_ad=757014031665&amp;hsa_src=g&amp;hsa_tgt=kwd-330992309681&amp;hsa_kw=systems%20engineering%20certificate&amp;hsa_mt=p&amp;hsa_net=adwords&amp;hsa_ver=3&amp;gad_source=1&amp;gad_campaignid=22653236069&amp;gbraid=0AAAAADMFzx_P1p0Wk29IBsERkHt3RNsSC&amp;gclid=Cj0KCQjww8rQBhDjARIsAE43KPNwL3F05oSsk_zFPj4NWbLgBw9Iy5upCZ61CQininiAvvORKBh8-SEaAm_wEALw_wcB" rel="noopener noreferrer" target="_blank">MIT's Architecture and System Engineering Online Certificate Program</a>.</p><p>In this episode, we'll explore the world of systems thinking, what it really means to see the connections between events, why the decisions you make early in any complex system can determine everything that follows, and how organizations consistently undermine themselves by optimizing the wrong things. From NASA to Amazon to Meta, Bruce has seen systems succeed and fail at the highest levels, and he's here to share what he's learned, including some surprises along the way.</p><p><strong>Mentioned links:</strong></p><ul><li><a href="https://xpro.mit.edu/programs/program-v1:xPRO+SysEngx/" rel="noopener noreferrer" target="_blank">Architecture and Systems Engineering: Models and Methods to Manage Complex Systems</a></li><li><a href="https://learn.mit.edu" rel="noopener noreferrer" target="_blank">MIT Learn</a></li></ul><br/>]]></content:encoded><link><![CDATA[https://teach-us-something-new.captivate.fm]]></link><guid isPermaLink="false">1952cbcb-2a21-4892-969f-1dc4ccf3286e</guid><itunes:image href="https://artwork.captivate.fm/f2db7950-e2d2-4c45-9aa3-c4727bf738e3/Teach-Us-Something-New-Graphic.jpg"/><pubDate>Mon, 25 May 2026 00:00:00 -0400</pubDate><enclosure url="https://episodes.captivate.fm/episode/1952cbcb-2a21-4892-969f-1dc4ccf3286e.mp3" length="86402950" type="audio/mpeg"/><itunes:duration>45:00</itunes:duration><itunes:explicit>false</itunes:explicit><itunes:episodeType>full</itunes:episodeType><itunes:season>1</itunes:season><itunes:episode>1</itunes:episode><podcast:episode>1</podcast:episode><podcast:season>1</podcast:season><podcast:transcript url="https://transcripts.captivate.fm/transcript/2804522d-7ca1-420b-ab9d-4abc056605e2/index.html" type="text/html"/></item></channel></rss>