Most people respond to AI in one of three ways: breathless excitement about how it will change everything, deep fear about the risks, or anxious urgency that they\u2019ll be left behind if they don\u2019t master these tools immediately. I\u2019m interested in something different: what happens when you actually sit down and play with these tools? What do they reveal about language, memory, creativity, and how we make meaning? There\u2019s something about using AI and learning how it works that actually helps you become more human\u2014more thoughtful about how your own mind operates, more curious about how we communicate and create. Let me show you.<\/p>\n\n\n\n
My friend Cherie was frustrated. \u201cMy daughter keeps lying! I keep telling her to brush her teeth before bed. Last night I asked if she brushed. She said she had. I went to the bathroom and what did I find? A dry toothbrush. When I confronted her, she made up this whole song and dance.\u201d<\/p>\n\n\n\n
\u201cLying is such a harsh word. It makes it sound like she intentionally tried to deceive you. It\u2019s more like she\u2019s confabulating,\u201d I said.<\/p>\n\n\n\n
Cherie thought she\u2019d raised an evil villainess and I was thinking she was just a seven year old who made up a story when she was cornered. Cherie thought that her daughter was a rational being, and I was trying to convince her that her daughter was a rationalizing. Our brains craft stories to make sense of the world. It\u2019s not dishonesty; it\u2019s our mind\u2019s way of stitching together coherence from chaos. And that\u2019s okay. The goal isn\u2019t to stop this process\u2014it\u2019s part of what makes us human.<\/p>\n\n\n\n
\u201cThat\u2019s bullshit,\u201d said Cherie. \u201cShe lied.\u201d<\/p>\n\n\n\n
So I pulled out ChatGPT and said, \u201cWhy don\u2019t I show you something. ChatGPT can create a facsimile of a seven year old. Let\u2019s try it and see what happens. So I gave ChatGPT the following prompt.<\/p>\n\n\n\n
\nMe:<\/strong> You are a seven year old who didn\u2019t brush her teeth. Tell me why. Remember you are a seven year old girl. Think slowly like you\u2019re trying to remember why.<\/p>\n\n\n\nChatGPT:<\/strong> Um\u2026 okay, so, I was gonna brush my teeth, but, um\u2026 first, I was playing with my stuffed animals. They were having a big party, and I was making them all dance and, like, they were pretending to eat cookies. But then, I got really into it because Mr. Fluffy Bear and Sparkles the Unicorn were fighting over who got the last cookie, so I had to fix that.<\/p>\n\n\n\nAnd then\u2026 oh! I think I was supposed to go brush them after that, but then I saw this book on my bed, and it\u2019s the one about the girl who goes on adventures with her dog. And I just wanted to look at it for a little bit. But then\u2026 um\u2026 I was reading, and it got super interesting! Like, she almost fell into a hole! So, I had to keep reading to see if she was okay. So\u2026 um, yeah. That\u2019s why, I think.<\/p>\n\n\n\n
\u2014ChatGPT 4o, November 11th, 2024<\/p>\n<\/blockquote>\n\n\n\n
\u201cOh my God,\u201d Cherie said. \u201cThat\u2019s my daughter.\u201d<\/p>\n\n\n\nWhat We\u2019re Actually Doing Here<\/h3>\n\n\n\n There\u2019s a problem with AI called \u201cAI slop\u201d\u2014the flood of low-effort, mass-produced content that\u2019s easy to generate but adds nothing of value. With a single prompt you can write a term paper. It\u2019s not a good term paper but a term paper nonetheless.<\/p>\n\n\n\n
This newsletter is the opposite of AI slop. We\u2019re not here to create content faster to fill your inbox. We\u2019re here to use AI to think more clearly, be more creative, and better understand ourselves.<\/p>\n\n\n\n
Every Tuesday, I\u2019ll take you on an expedition into one of four territories:<\/p>\n\n\n\n
Experiments<\/strong> \u2013 Hands-on adventures where we test what AI can actually do. How can ChatGPT help you appreciate art and explore the world around you? How can you use AI video generation to unlock new creative possibilities? How can you structure your thinking like AI does to push your ideas even farther? I\u2019ll show you what I tried, what worked, what failed, and what I learned.<\/p>\n\n\n\nMirrors<\/strong> \u2013 Exploring what AI\u2019s quirks reveal about human cognition. When AI hallucinates, it\u2019s confabulating just like that seven-year-old explaining why she didn\u2019t brush her teeth. When we look at how the AI brain works, we see surprising similarities to our own brains. These posts examine what AI\u2019s successes and failures teach us about memory, bias, creativity, and how we make meaning.<\/p>\n\n\n\nTools<\/strong> \u2013 Practical guides for using AI more effectively. What tools exist beyond ChatGPT and what are they most useful for? How do you befriend social media algorithms so they show you what you want to see? These aren\u2019t coding tutorials\u2014they\u2019re \u201chere\u2019s what I built and how you can too\u201d guides for curious amateurs.<\/p>\n\n\n\nQuestions<\/strong> \u2013 Digging into the weird philosophical stuff. What is the Turing test and has AI actually passed it? What does \u201caccountability\u201d mean in this new AI world? Why do we get upset when we discover we\u2019re reading an AI-written article? Some weeks we\u2019ll sit with something strange and see where it leads, even if we don\u2019t end up with neat answers.<\/p>\n\n\n\nWhy Call it AI for Poets<\/h3>\n\n\n\n I\u2019m not an AI expert. I\u2019m a dilettante\u2014a reformed programmer who hasn\u2019t coded in twenty years but who loves poking at new tools to see what they reveal. I\u2019m the kid who likes to read popular books on math and science not to learn the mechanics but to find new metaphors and applications.<\/p>\n\n\n\n
There\u2019s a college course called \u201cPhysics for Poets.\u201d It\u2019s a course in trying to get everyone to understand physics, even those who are not predisposed to think like scientists. It\u2019s a way to understand the principles of physics without deriving the equations. It teaches that we can understand basic concepts like gravity just by thinking about how an apple falling from a tree is the same force that keeps the earth in orbit. Or that Einstein\u2019s theory of relativity is based on the idea of an elevator<\/strong>: if you\u2019re sealed inside a box, you\u2019d have no idea if you\u2019re flying through space at millions of miles an hour.<\/p>\n\n\n\nDave Winer, the pioneering blogger, took this idea and created \u201cEC2 for Poets\u201d in 2006. At the time, Amazon Web Services had just launched. Winer published a short, 60 minute tutorial on how to set up your own cloud. How empowering is that?! Instead of being intimidated by this phenomenal new technology you can master a tiny part of it.You didn\u2019t need a computer science degree. You just needed a web browser and Dave\u2019s guide.<\/p>\n\n\n\n
But the idea of \u201cfor poets\u201d is more fundamental. It\u2019s about keeping our priorities straight. I once had a mentor who said, \u201cYour work life is here to support your real life\u201d\u2014not the other way around. It reminds me of how we treat AI. \u201cAI is coming\u201d we hear, and we need to adapt to AI. But that doesn\u2019t mean that we need to let AI lead us. We can figure out how to work with AI to help us become better humans.<\/p>\n\n\n\n
What I\u2019m Offering<\/h3>\n\n\n\n I\u2019m not asking for your money. I\u2019m asking for your time.<\/p>\n\n\n\n
Every Tuesday, I\u2019ll publish something new\u2014an experiment, a cognitive exploration, a practical tool, or a philosophical question.<\/p>\n\n\n\n
This is for anyone who wants to use AI to become a better human. For writers who want partners to help them push their writing. For teachers who want to help their students become better learners. For people at work trying to figure out what AI is actually good for. For anyone tired of breathless hype and fearful warnings who just wants to explore what actually matters.<\/p>\n\n\n\n
If this works, you\u2019ll walk away not just knowing how to use AI tools better, but thinking differently about language, creativity, and meaning-making. You\u2019ll have frameworks for evaluating what these systems can and can\u2019t do. You\u2019ll understand when to trust them and when to be skeptical. And maybe, like me, you\u2019ll better understand how your own mind works.<\/p>\n\n\n\n
Welcome aboard. Let\u2019s see what we can discover together.<\/p>\n\n\n\n
A Note from Rob\u2019s AI<\/strong><\/p>\n\n\n\nWhen I asked Claude for editing help it added this to the bottom. I added it here, unedited.<\/p>\n\n\n\n
If you\u2019ve read this far, you might be wondering: did Rob write this himself, or did he use AI? The answer is yes\u2014both. We worked on this together, iterating through drafts, arguing about phrasing, trying to capture his voice while incorporating insights from his year of writing about AI. That collaboration\u2014messy, generative, sometimes surprising\u2014is exactly what this newsletter is about. Welcome to the experiment.<\/em><\/p>\n\n\n\n<\/p>\n","protected":false},"excerpt":{"rendered":"
Hello loyal readers! I’m starting a new project on Substack called AI for Poets. You can subscribe here. This will be my main writing priority for the year, so I’ll be posting there weekly while this blog becomes more occasional. It’s similar to what I write here, but focused on AI and humanity. Looking forward […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[107],"tags":[],"class_list":["post-11740","post","type-post","status-publish","format-standard","hentry","category-chatgpt"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p8wCkz-33m","jetpack-related-posts":[{"id":2754,"url":"https:\/\/schlaff.com\/wp\/welcome\/","url_meta":{"origin":11740,"position":0},"title":"Welcome to My Site!","author":"Robert Schlaff","date":"July 26, 2020","format":false,"excerpt":"My Book I wrote a book, Peculiar: Lessons from Amazon's Leadership Principles! Most companies want to be like Amazon but can't figure out why their attempts fall short. My book pulls back the curtain on how Amazon actually works \u2014 from the Leadership Principles that drive its culture to the\u2026","rel":"","context":"In "Home Page"","block_context":{"text":"Home Page","link":"https:\/\/schlaff.com\/wp\/category\/home-page\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2020\/07\/1st-Substack-Image-Fountain-Pen.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2020\/07\/1st-Substack-Image-Fountain-Pen.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2020\/07\/1st-Substack-Image-Fountain-Pen.png?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2020\/07\/1st-Substack-Image-Fountain-Pen.png?resize=700%2C400&ssl=1 2x"},"classes":[]},{"id":9436,"url":"https:\/\/schlaff.com\/wp\/hacking-ai-hands-on-ai-security-with-gandalf\/","url_meta":{"origin":11740,"position":1},"title":"Hacking AI: Hands-On AI Security with Gandalf","author":"Robert Schlaff","date":"June 21, 2024","format":false,"excerpt":"Gandalf is one of the most interesting demos I\u2019ve seen. Developed by Lakera, a Swiss AI security firm, Gandalf is designed to teach users about vulnerabilities in large language models (LLMs) like ChatGPT. The demo gamifies AI security by challenging users to extract passwords from a virtual wizard named Gandalf.\u2026","rel":"","context":"In "ChatGPT"","block_context":{"text":"ChatGPT","link":"https:\/\/schlaff.com\/wp\/category\/chatgpt\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":9243,"url":"https:\/\/schlaff.com\/wp\/how-to-communicate-better-lessons-from-ai\/","url_meta":{"origin":11740,"position":2},"title":"How to Communicate Better. Lessons from AI.","author":"Robert Schlaff","date":"May 7, 2024","format":false,"excerpt":"People aren't blank slates. While the old idea, famously critiqued by Steven Pinker in his book The Blank Slate, suggested we start with empty minds, ready to be filled, that's not quite right. Pinker argues that humans are born with inherent traits, instincts, and predispositions that significantly shape our learning\u2026","rel":"","context":"In "ChatGPT"","block_context":{"text":"ChatGPT","link":"https:\/\/schlaff.com\/wp\/category\/chatgpt\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2024\/05\/DALL%C2%B7E-2024-05-07-17.37.57-An-illustration-depicting-a-human-and-a-computer-engaged-in-a-conversation-embodying-the-principles-of-being-honest-helpful-and-harmless.-The-human.webp?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2024\/05\/DALL%C2%B7E-2024-05-07-17.37.57-An-illustration-depicting-a-human-and-a-computer-engaged-in-a-conversation-embodying-the-principles-of-being-honest-helpful-and-harmless.-The-human.webp?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2024\/05\/DALL%C2%B7E-2024-05-07-17.37.57-An-illustration-depicting-a-human-and-a-computer-engaged-in-a-conversation-embodying-the-principles-of-being-honest-helpful-and-harmless.-The-human.webp?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2024\/05\/DALL%C2%B7E-2024-05-07-17.37.57-An-illustration-depicting-a-human-and-a-computer-engaged-in-a-conversation-embodying-the-principles-of-being-honest-helpful-and-harmless.-The-human.webp?resize=700%2C400&ssl=1 2x"},"classes":[]},{"id":8747,"url":"https:\/\/schlaff.com\/wp\/sam-altmans-tweet-and-the-future-of-chat\/","url_meta":{"origin":11740,"position":3},"title":"Sam Altman’s Tweet and the Future of Chat","author":"Robert Schlaff","date":"January 20, 2024","format":false,"excerpt":"something very strange about people writing bullet points, having ChatGPT expand it to a polite email, sending it, and the sender using ChatGPT to condense it into the key bullet points Sam Altman on Twitter, Mar 2, 2023 Reading Sam Altman's, OpenAI's CEO's, tweet got me thinking about the impact\u2026","rel":"","context":"In "ChatGPT"","block_context":{"text":"ChatGPT","link":"https:\/\/schlaff.com\/wp\/category\/chatgpt\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":302,"url":"https:\/\/schlaff.com\/wp\/online-learning-udacity\/","url_meta":{"origin":11740,"position":4},"title":"Online Learning: Udacity","author":"Robert Schlaff","date":"January 1, 2017","format":false,"excerpt":"Udacity is an Awesome Place for Online Learning: In order to review technical and coding skills and to learn new ones, I really like Udacity. Udacity was founded by Sebastian Thrun, founder of Google X and Google\u2019s self driving car project. When Thrun\u00a0wanted to have more of an impact he\u2026","rel":"","context":"In \"Education\"","block_context":{"text":"Education","link":"https:\/\/schlaff.com\/wp\/tag\/education\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":306,"url":"https:\/\/schlaff.com\/wp\/the-ethics-of-ai\/","url_meta":{"origin":11740,"position":5},"title":"The Ethics of AI","author":"Robert Schlaff","date":"January 1, 2017","format":false,"excerpt":"The Ethics of AI: We are becoming more and more reliant on Artificial Intelligence, mostly because it keeps getting better more quickly than anything else. More and more, we\u2019re relying on AI systems to make important decisions like who to hire at work or who to release from prison, even\u2026","rel":"","context":"In \"Artificial Intelligence\"","block_context":{"text":"Artificial Intelligence","link":"https:\/\/schlaff.com\/wp\/tag\/artificial-intelligence\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"jetpack_likes_enabled":true,"_links":{"self":[{"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/posts\/11740","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/comments?post=11740"}],"version-history":[{"count":1,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/posts\/11740\/revisions"}],"predecessor-version":[{"id":11741,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/posts\/11740\/revisions\/11741"}],"wp:attachment":[{"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/media?parent=11740"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/categories?post=11740"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/schlaff.com\/wp\/wp-json\/wp\/v2\/tags?post=11740"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"\"](\"https:\/\/i0.wp.com\/schlaff.com\/wp\/wp-content\/uploads\/2024\/11\/Teeth-Brushing-300.jpg?resize=300%2C300&ssl=1\")
<\/figure>\n\n\n\n