Out of Our Depth

Mary and Josh
  • 0.0 (0)
  • Technology
  • Updated Semiweekly

Out of Our Depth is us learning AI out loud... breaking down new developments, testing the tools, and asking the silly questions so you don't have to.

Episodes

  1. 1d ago

    [BONUS EPISODE] The Art of Personalization: Teaching AI YOUR voice & style

    Why does everyone's AI sound the same, and how do you make yours sound like you? In this live AI@GSB workshop at Stanford GSB, Mary Blankemeier shows how to teach AI your voice and your visual style with skills: give it examples, the vibe you want, and your icks, then keep updating the skill every time you correct it.Build your own with the tutorial: https://aigsb-workshop3.vercel.appQuestions, ideas, feedback? Drop them in the comments or email hi@outofourdepth.com.0:00 Who I am0:53 The plan: five questions1:28 Which website would you trust?2:50 Why AI drifts to the average4:27 When it feels AI-made, trust drops6:09 What's a skill?7:30 Your voice: examples, vibe, icks8:21 Skills get good by iterating9:36 Update the skill every time you correct it10:43 Q&A: keeping only the parts of your voice you like12:35 Your design: same formula15:15 The payoff: one brand skill, a whole platform18:02 Rapid fire: what I wish I knew sooner20:31 Split skills that don't travel together21:35 Context, explained with an intern and a messy desk22:31 My favorite skills23:51 Q&A: what if your writing already sounds like AI?24:48 Go build

  2. 6d ago

    Will AI Take Our Jobs? What AGI Actually Means

    Will our jobs still exist when we graduate? We get into what artificial general intelligence (AGI) actually means, how close we think we are, and what it could change about work and everyday life. Josh thinks we could have AI that feels like AGI by the end of 2027. Mary wants it to prove it can handle a real person's breadth of tasks, depth of judgment and reliability. Naturally, the conversation turns to whether it can even be trusted with her inbox. We unpack the "jagged frontier," why the goalposts keep moving, whether AI can improve itself, and what benchmarks can tell us. Then we get into the harder questions: what does adapting look like when you're already working and raising a family? Who gets a say in how this technology develops? And what would a future worth being optimistic about actually look like? Plus, Mary's vision for a world with more opportunity, a debate about work and purpose, and a one-year challenge involving AI, friendship and FaceTime. Try this: pick a task you know well. Decide what reliable, end-to-end help would look like, then test an AI tool against that standard. What would convince you we've reached AGI? Tell us your test in the comments. Chapters 00:00 AGI and our jobs 01:06 What would count as AGI? 04:01 The moving goalposts 05:15 Can AI improve itself? 07:27 Our AGI predictions 09:10 Why email is harder than it looks 13:48 Can tests settle the debate? 15:17 Reasons to stay optimistic 18:13 Who needs a voice in AI? 19:44 The downside case 21:51 Adapting when you have no spare time 25:50 Staying curious in uncertainty 26:59 Who should get access? 28:43 The future we want 33:40 Our one-year test Out of Our Depth: https://outofourdepth.com Instagram: https://www.instagram.com/outofourdepthpod/ Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Go deeper Google DeepMind - Levels of AGI: https://deepmind.google/research/publications/66938/ ARC Prize / ARC-AGI benchmarks: https://arcprize.org/ Questions or episode ideas? hi@outofourdepth.com

  3. Oct 17

    How to Learn AI Without Feeling Behind

    Feeling behind on AI? So are we. We're building an AI "couch to 5K": a manageable way to understand the language, get comfortable with tools like ChatGPT and Claude, and form our own views on the bigger questions. In this episode, we compare what's helping us learn, from explanations built around things we love to small weekly experiments. Mary brings the girly pop energy. Josh confronts his newsletter overload and an app that probably didn't need to be an app. Try this with us: pick one AI term you keep hearing, ask ChatGPT or Claude to explain it through something you love, then use it on one small, real task this week. At the end, we show you our new Learning tab, where you can browse AI terms, vote for topics you want us to cover, and suggest anything we've missed. CHAPTERS 00:00 Ask the question anyway 02:42 From zero to one 05:32 Fluency, agency and perspective 08:16 Build an information diet you will use 10:47 Make the learning stick 12:42 Build your fluency base 14:46 Agency: start with one useful thing 17:19 Solve the problem before building the app 20:53 Perspective: choose questions that matter 27:55 What is known, unknown and worth exploring 30:32 Fact-check and listen to the stakes 31:57 Keep us honest: measure progress 32:47 Explore the Learning tab and vote EXPLORE WITH US Website: https://outofourdepth.com Learning tab and topic requests: https://outofourdepth.com/learning RESOURCES MENTIONED Ben's Bites: https://www.bensbites.com Ethan Mollick / One Useful Thing: https://www.oneusefulthing.org tldraw: https://www.tldraw.com Gallup's April 2026 survey on Gen Z and AI: https://news.gallup.com/poll/708224/gen-adoption-steady-skepticism-climbs.aspx

  4. Oct 11

    AI Planned Our Wedding

    We planned our wedding with AI. Mary gave Josh a trial period... if it got stressful, we would hire a real wedding planner. In this episode, we walk through what we actually used it for, from comparing venue packages and building a detailed task tracker to figuring out which linens, hair and makeup felt right. Mary brings the design judgment. Josh gets very into the logistics. Both of us get a little excited about planning another wedding. We also share how we built a wedding weekend website with schedules, photo sharing and a few jokes for our guests. Then we talk about using voice memos to organize memories before writing our own vows. Try this: give AI the details of your next big project, ask what information is missing, and have it turn the plan into tasks with owners and deadlines. Bring examples of what you like when a decision is hard to picture. What's one part of wedding planning you'd want help with? Tell us in the comments or email hi@outofourdepth.com. Chapters 00:00 Planning our wedding with AI 02:30 Find the right venue 03:58 Compare venue packages and costs 06:09 Questions for the venue tour 08:01 Build a wedding task tracker 11:23 Give AI your wedding preferences 13:35 Keep your planning context up to date 16:45 Visualize the venue and decor 20:47 Find hair and makeup that feel like you 23:53 Build a wedding weekend website 25:50 Make the weekend easier for guests 30:11 Connect the website to your guest list 31:01 Organize memories for your vows 32:04 Keep wedding planning fun Out of Our Depth: https://outofourdepth.com Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Tools we mention ChatGPT: https://chatgpt.com Claude: https://claude.ai Gemini: https://gemini.google.com Granola: https://www.granola.ai Canva: https://www.canva.com Pinterest: https://www.pinterest.com Zola: https://www.zola.com Related episode Projects, Connectors & Skills... Take Your AI from Fresh Intern to Full-Time Hire: https://www.youtube.com/watch?v=d-ykZl4WHjo #AI #Podcast #OutOfOurDepth

  5. Oct 9

    How to Make AI Actually Sound Like You

    In this episode, we work through how to make AI’s writing and designs reflect your voice, taste, and brand. Mary shares how she built Run Your City’s design system by asking for options, reacting to examples, and refining what felt right. Josh walks through teaching AI his writing style with real emails, Slack messages, and feedback, then adapting those instructions for different audiences. We also get into AI’s role in Mary’s painting process, borrowing visual inspiration, and how we use reusable skills in our grant applications while keeping people involved in the final review. Try this: ask your AI for three versions, explain what you like and what feels off, and turn those choices into instructions you can reuse. Chapters 00:00 Personal site, personal style 01:05 Make AI reflect your brand 05:41 Design that feels like you 07:33 From design system to reusable skill 09:44 How to get started 11:48 AI in Mary's creative process 15:46 Borrow inspiration 17:31 Write for the person reading 19:14 Teach AI your writing style 25:05 Audience, format and feedback 28:20 Our grant-writing workflow 32:11 Keep the human review Out of Our Depth: https://outofourdepth.com Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Ideas for a future episode: hi@outofourdepth.com Tools and resources Winning Writing skills: https://github.com/kalyvask/winning-writing Humanizer skill: https://github.com/blader/humanizer Claude Design: https://claude.com/product/design Try it yourself Set up a design system in Claude Design: https://support.claude.com/en/articles/14604397-set-up-your-design-system-in-claude-design Create your own Claude skill: https://support.claude.com/en/articles/12512198-how-to-create-custom-skills Related episode Projects, Connectors & Skills… Take Your AI from Fresh Intern to Full-Time Hire: https://www.youtube.com/watch?v=d-ykZl4WHjo

  6. Oct 6

    ChatGPT as Our Running Coach: What We Had to Fix

    We need to prepare for El Cruce, a three-day mountain race. Mary wants a coach, cute gear and the logistics handled. Surely AI can sort all that out… right? We turn a messy brainstorm into ChatGPT project instructions, compare voice with dictation, and build a training website we actually want to use. The first version needs work. So do our instructions. Along the way, we figure out how to give AI useful context, bring examples of what we like, ask for a plan before it starts building, and stop when something is good enough. Plus a few reminders that learning AI together can get chaotic. Try this on your own project: give AI your goals and constraints, ask what information is missing, then request three possible output formats before it starts building. 00:00 Our adventure and the AI brief 04:35 Turn a brainstorm into useful context 09:09 Save instructions and test voice 12:23 Ask for a plan before it builds 14:14 What the AI asks before planning 16:23 Your taste belongs in the prompt 18:19 Bring examples the AI can use 20:06 Review the first result 21:56 Define what good enough means 23:52 A website we want to use 25:18 Share the website 27:15 Now for the logistics 28:32 Better thinking beats more prompting 31:52 Good enough and learning together

  7. Oct 4

    What the Heck is an AI Agent?

    Everyone keeps talking about AI agents. We wanted to understand what actually makes something an agent, so naturally we explain it with eggs. Then we give the eggs a manager. Meet Big Egg. We break down how agents work, what they can do for us, and why asking one to do everything at once usually goes badly. Mary gives Muse about five minutes to impress her, Instinct emails about her overdue Revolve returns, and Josh uses Dottie to find Mary a bike. We also get into Anthropic's vending-machine experiment and explain outcome-based pricing with a very hypothetical Planet Fitness. What's your favorite personal agent, and how do you like your eggs? Drop both in the comments or email hi@outofourdepth.com. These are equally important questions. Chapters 00:00 What actually is an AI agent? 01:59 What goes into an agent 03:21 How an agent works through a task 04:17 Chatbots vs. automations vs. agents 06:12 Meeting notes that turn into follow-ups 07:24 How agentic is it? 08:29 Mary's five-minute test 09:52 What can Muse actually do? 10:53 Instinct and the overdue returns 12:17 Voice memos and emailing Mary's TA 13:25 Dottie, Muse and Grokbot 14:50 Finding Mary a bike 16:08 Stop asking it to do everything 17:41 Big Egg and the agent team 19:13 Do you need all those agents? 20:17 Our ultramarathon planning mistake 21:18 Project Vend: the blue blazer 22:35 Better tools, better guardrails 23:40 How do agents make money? 24:32 Paying for results 25:44 Explain it with a gym 27:58 Recap: what the heck is an agent? 30:17 How do you like your eggs? 31:55 Phone a friend: the runny boil Out of Our Depth: https://outofourdepth.comRun Your City: https://www.runyourcity.orgAI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-aiResearch notesProject Vend, including the blue-blazer story: https://www.anthropic.com/research/project-vend-1More on agents, workflows and when a simpler setup is enough: https://www.anthropic.com/engineering/building-effective-agentsOur personal-agent reviews reflect what we tried at the time. The Slack prices and gym pricing models are examples, not actual offers.

  8. Oct 4

    ChatGPT vs Claude vs Gemini: What's the Difference?

    Claude, ChatGPT, Opus, Astra, tokens, open weights... if you've ever nodded along to an AI conversation while secretly having no clue what anyone meant, this one's for you. (Us too. Like, yesterday.) This is our who's who of AI: who actually builds the models, the difference between a model and the app you're typing into (the model is the engine, the app is the car, and tokens are the gas; stay with us). Then it gets a little spicy. Mary thinks the world's best mathematicians are about to matter less, Josh disagrees, and we rank Demis, Dario, Sam, and Elon from most to least loved. What AI word do you still secretly not understand? Drop it in the comments or email hi@outofourdepth.com and we'll tackle it. No stupid questions (we asked most of them in this episode). Chapters 00:00 Data centers on the moon? + AI intro 01:09 Who actually builds the models 02:20 Claude vs. ChatGPT: what we actually use 05:12 Gemini, the Dodgers of AI 06:20 Open vs. closed: how models learn 08:49 The car analogy: models vs. apps 12:28 Why are the model names so bad? 13:26 Tokens are gas 14:35 Are mathematicians out of a job? 18:33 Jobs vs. tasks 20:16 Who gets left behind 21:36 Mary's coding midterm (29 or 92?) 24:18 What's overhyped 24:59 What we're betting on: being human 27:14 NVIDIA and the wider AI market 28:22 Why it's so easy to switch 29:44 How do open models make money? 33:05 On-prem vs. the cloud (and the moon) 35:05 Dario and the Anthropic origin story 37:40 When AI breaks the rules 42:07 Sam, Zuck, and Elon 45:56 Ranking the AI leaders 49:21 Mary's last three AI chats and goodbye Out of Our Depth: https://www.outofourdepth.com Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Research notes: On AI and math: OpenAI published ten results in mathematics and theoretical computer science obtained by an internal model. These are the company's reported findings; our discussion about what they mean for mathematicians is opinion. Read the report: https://cdn.openai.com/pdf/ten-proofs-oai.pdf More on Astra and the math results: https://the-decoder.com/openai-announces-its-next-major-model-astra-by-dropping-ten-previously-unsolved-math-solutions On Demis: Google announced that Demis Hassabis handed over day-to-day Google DeepMind operations to become its chair and Alphabet's chief scientist: https://blog.google/company-news/inside-google/message-ceo/next-chapter-ai-momentum

  9. Sep 30

    Claude/ChatGPT Skills, Projects & Connectors, Explained Simply

    Ever asked AI something and gotten an answer so generic it could've been for anyone? Same. These are the three features that fixed that for us: projects, connectors, and skills. We use them every day and tell our friends to set them up first. We explain all three with one very committed intern metaphor, then get into what we've actually built: a grant finder that posts straight into our nonprofit's Slack, a newsletter that reads Josh's 20 other newsletters so he doesn't have to, and the brand skill Josh stole from Mary. Also, Josh cannot go to bed with unused AI credits. What's the most repetitive thing you do every week? Drop it in the comments or email hi@outofourdepth.com and we might try turning it into a skill on the show. Chapters 00:00 Intro: why these three features 01:43 Projects: give your AI a desk 04:56 Mary's fitness project 05:59 Connectors, Granola and recording consent 08:12 Skills: reusable workflows 08:45 Josh's bank account skill 09:56 Teaching a skill by showing the workflow 10:49 Projects vs. skills (hello, Dyslexify) 11:56 Claude Design and Wispr Flow 13:40 Leveling up your intern 14:33 The brand skill Josh stole from Mary 15:42 Humanizer: less AI slop 16:29 The skills behind this podcast 17:23 Josh vs. unused credits 19:01 Why AI tells make people tune out 19:49 Composio: connecting multiple accounts 21:43 Recap: projects, connectors and skills 22:22 One newsletter instead of 20 23:37 A grant finder for Run Your City 26:07 Rebuilding our whole website 27:52 Why human effort still matters 29:53 Where AI missed the mark 32:09 What's next: agents Out of Our Depth: https://outofourdepth.com Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Tools we mention Composio: https://composio.dev Granola: https://www.granola.ai Wispr Flow: https://wisprflow.ai Humanizer skill: https://github.com/blader/humanizer No AI Slop skill: https://github.com/petergyang/no-ai-slop

  10. Sep 30

    We Can’t Keep Up with AI Either (So We Started a Podcast!)

    We got married a few weeks ago, started our second year of business school at Stanford, and apparently thought now was a great time to start a podcast. About AI. A thing we’re very much still figuring out ourselves. This first one is mostly us: who we are, why we’re doing this, and why we think everyone should be learning AI (yes, even the haters). We also talk about running a youth sports nonprofit together, the 15-ish puppies we’ve fostered, and the time Josh had AI make family holiday photos of our future kids on our honeymoon. What should we try next? Drop it in the comments or email hi@outofourdepth.com. We read everything (…there’s not much yet). Chapters 00:00 Why we’re here 01:14 Why learn AI together 02:08 Making it fun and accessible 03:45 Meet Josh and Mary 05:01 Run Your City 06:00 What to expect 06:48 Curious and skeptical 08:05 Fun facts 08:47 The honeymoon AI photo experiment 10:28 Closing invitation Out of Our Depth: https://outofourdepth.com Run Your City: https://www.runyourcity.org AI@GSB: https://www.gsb.stanford.edu/experience/learning/applied-ai Research note: when we say women are "20% behind," that's the relative gap in generative AI use from a 2025 analysis of 18 studies: https://www.hbs.edu/ris/Publication%20Files/25023_52957d6c-0378-4796-99fa-aab684b3b2f8.pdf

  • 1 Trailer
    9 Episodes

Trailer

About

Out of Our Depth is us learning AI out loud... breaking down new developments, testing the tools, and asking the silly questions so you don't have to.

Information

  • Creator
    Mary and Josh
  • Years Active
    2026
  • Episodes
    10
  • Rating
    Clean
  • Copyright
    © Mary and Josh
  • Show Website
    Out of Our Depth

You Might Also Like