The JEN AI Podcast

Episode 15: A Bathrobed Keynote, How to use AI to Make Tech Products, Leaving Google, and The Devil Wears Prada Meets Silicon ValleyIn episode 15 of JEN_AI, Jenni Munroe (formerly Google/DeepMind) recounts giving a main-stage keynote at Future Product Days in Copenhagen wearing a bathrobe and dog slippers while demoing how AI tools can help anyone create a product, using a makeup/wardrobe “makeover” app and an onstage outfit transformation with audience volunteers. She shares a three-step framework - define the problem with Gemini Deep Research, build a prototype in Google AI Studio, and create a promo video with Flow or Google Vids - plus tips. She reflects on the talk, leaving Google, and revisting 'The Devil Wears Prada' after 20 years in honor of the upcoming sequel. She describes a failed attempt to get Gemini to reproduce the Devil Wears Prada “blue sweater” speech, notes Allbirds’ surprise pivot to “Bird AI” cloud GPUs, and shares a themed soundtrack.00:00 The Fluffy Bathrobe Keynote Speech 01:04 Who Is JEN_AI?01:57 How The Talk Happened03:18 Three Steps To Build Your Own Products With Google AI Tools03:44 Problem Research With Google Gemini04:33 Prototype With Google AI Studio05:09 Promo Video With Google Flow05:49 Tips And Tool Comparisons07:28 How It Went And Lessons10:11 Remaking Work And Life11:07 Devil Wears Prada Skit Fail14:02 Allbirds Shoes Pivot To GPUs14:50 Soundtrack Picks And Wrap This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

Bridging Worlds: Nobel-Winning Breakthroughs & Quantum ComputingIn this episode, Jenni Munroe explores the significance of a recent Nobel Prize awarded to quantum researchers for their groundbreaking experiments from the 1980s. These experiments demonstrated that quantum effects could be harnessed on a macroscopic scale, paving the way for today's advancements in quantum computing. The script delves into the principles of quantum mechanics, notable achievements like quantum supremacy, and the challenges and potential of quantum computing. Additionally, it discusses the ongoing quest to unify quantum mechanics with general relativity and highlights the profound impact of these scientific advancements on technology and our understanding of the universe.00:00 Intro to the JEN_AI Quantum Science Communication Challenge00:29 2025 Nobel Prize in Quantum Physics02:08 WTF is a Quantum? Understanding Quantum Mechanics03:11 Schrodinger's Cat Explained04:55 Breakthroughs in Quantum Science08:14 Quantum Computing Revolution10:08 Our Divided World: Challenges in Quantum Science15:39 A Quantum of Hope: Quantum Electrodynamics (QED)18:09 Reflections This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

Challenge #12.5: Use AI to Present a TED TalkJenni Munroe, host of JEN_AI, tackles her latest challenge: using AI tools to create and deliver an inspirational TED-style talk to 100 computer science students. She highlights her process of leveraging chatbots like ChatGPT and tools like Gamma App to generate her presentation deck. Despite feeling rusty after returning from maternity leave, she shares clips from the talk touching on imposter syndrome, the importance of experimenting, and cultivating a public personal brand. She draws inspiration from model Cameron Russell's TED talk and emphasizes the significance of sharing one's goals and work with others. Additionally, the episode features a segment about artist Maggie Rogers' breakout music moment, stressing the importance of sharing your art and your authentic self with the world. You don't need to be perfect, you just need to start.00:00 Introduction and Challenge Overview00:53 Creating the Talk with AI01:44 Slide Generation and Presentation03:15 Reflections on the Talk04:23 Inspiration from Cameron Russell05:58 Experimentation and Progress07:23 Overcoming Self-Doubt09:16 Building Your Personal Brand11:49 Conclusion and Final Thoughts This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

JEN_AI Makeover: Can Technology Help Us Become Who We Were Meant to Be?In this episode of JEN_AI, Jenni Munroe, a Google generative artificial intelligence (GenAI) enthusiast returning to work from maternity leave, takes on the challenge of an AI-assisted work-appropriate makeover. Jenni experiments with various AI tools like Facetune, Aragon AI, and Google's virtual try-ons to achieve a digital glow-up. She also collaborates with her stylish best friend, Hara from Amazon Web Services, for a real-world wardrobe refresh. The episode includes insights from a chat with Hara about personal style and identity, as well as a nod to inspirational shows like Queer Eye and RuPaul's Drag Race. Throughout, Jenni humorously navigates the interplay between AI's artificial enhancements and genuine self-expression.00:00 Welcome to JEN_AI00:36 Introducing the AI Makeover Challenge04:52 AI Tools for Virtual Makeovers07:12 Creating a Custom AI Makeover App11:57 Real-Life Makeover with a Stylish Bestie13:52 In-Depth Chat on Style and Personal Branding22:29 Embracing Personal Transformation23:50 The Power of Self-Expression25:31 Advice on Personal Growth28:58 Exploring AI in Daily Life34:05 Reflections on Makeovers and Identity38:04 Final Thoughts and Gratitude This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

Exploring AI: Hackathons, Vibecoding Project Showcase Websites, and the Chaotic World of JEN_AIIn this episode of the JEN_AI Blogcast, host Jenni Munroe dives into the chaotic and fascinating world of AI tools, tech, and digital media while reflecting on life as a human in the age of AI. Recently back at Google, Jenni introduces JEN_AI Series Two, which includes collaborative hack challenges to create AI-human projects, including a showcase website "vibecoded" using Google's AI Studio. The episode also covers recent AI news, and music by Sabrina Carpenter sets the tone as Jenni shares insights, hack fails, and encouragement for listeners to create and explore AI experiments.Google's AI Studio: ai.studioJEN_AI's demo showcase: jenai.studio00:00 Introduction to Gen AI00:34 Series Two: Vibe Mode Season00:54 Gen AI Challenge 11: Project Showcase01:28 Building with Google's AI Studio02:05 Pro Tips for Using AI Studio04:15 Showcase Results and Reflections06:09 AI News Highlights07:56 Soundtrack and Closing Thoughts09:18 Final Remarks and Credits This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

JEN AI Episode 10: There's No Page Like HomeIn this episode of JEN AI, host Jenni Munroe embarks on a challenge to create a website that generates custom homepages using AI tools. She explores the process of 'vibecoding' using platforms like Replit, shares the concept behind her project 'No Page Like Home', and reflects on the intricacies and emotional facets of digital and real-life homes. Jenni also shares her personal journey of moving from London to California, dealing with family separation during the pandemic, and the joy of returning home. The episode wraps up with heartfelt reflections and thematic music recommendations.No Place Like Home webpage creator (demo): noplacelikehome.comJEN AI website: jenai.com00:00 Introduction to JEN AI Episode 1000:20 The Challenge: Building a Homepage with AI01:07 Exploring AI Tools for Website Creation02:15 Launching the JEN AI Website02:44 Creating a Digital Home: "No Place Like Home" Features and Vision04:52 "No Place Like Home" Prototype and User Experience06:13 Personal Project: A Homemade Website for Mother's Day07:01 Reflections on Dreams, Homes, and Life08:17 Family Reflections This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

In the 9th episode of the Jen AI series, host Jenni Munroe takes a moment for introspection and retrospection, encouraging listener feedback and summing up key takeaways from previous AI challenges. Jenni gives a rundown of her journey with Jen AI, considers when to follow advice vs. follow your heart, and examines learning from feedback in the context of both AI and personal growth. The episode also features an AI-generated podcast made with Google Gemini and NotebookLM tools, giving an extensive deep dive into the mechanics of neural networks, their historical development, application examples, and how they process language. The discussion includes real-world challenges and ethical considerations, offering up a chatbot's own insights into the impact of AI.00:00 Intro: This week on Jen AI00:31 Listener Feedback and Reflections00:55 Part 1: Jen AI Challenge Recap04:32 Part 2: Feed the Machine (give feedback!)05:29 Part 3: Giving Feedback on Feedback11:11 Deep Dive into Neural NetworksHere's the link to the JEN_AI insider poll - check it out! This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

This week's episode of the JEN_AI project, hosted by creative technologist Jenni Munroe, focuses on Challenge #8: 'Build Something Good.' The discussion is centered around the recent cuts in international aid by the US, UK, and EU, and features insights from international development expert Bridget Brown. After a ban from Twitter/X thwarts her Twitter bot, Jenni demonstrates how AI can be used to create a simple web app to send emails to government reps highlighting the importance of international aid. The episode underscores how aid functions as not just charity but security and economic & strategic muscle, while also introducing the concept of innovative, neurodivergent business models with guest Cressida Kocienski, a storytelling videographer who talks about her new initiative, Feral Business. The show wraps up with humor, political jabs, and references to popular culture, aiming to kindle socially-aware technological innovation.00:00 Intro to the Jen AI Challenge00:41 The Importance of Being Good02:10 Global Context and Aid Cuts04:05 Interview with Bridget Brown11:06 Meme Storytelling and 'Aid as Defense'13:48 Project LEMONAID19:27 Cressida Kocienski's Feral Business22:22 Thanks, JenAI Playlist & References This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

🔮 JEN_AI Challenge #007: Social Mediums. Exploring Social Media and AI: An Immersive JourneyIn this episode, we dive deep into the chaotic world of social media through the lens of generative AI, exploring 15 different platforms and creating a personality matrix to understand their quirks. The host goes undercover at a university to confront the discomforts of big tech and the generational divide. Listener engagements, real-life AI applications, and thought-provoking reflections on AI's impact on society are shared. Practical advice on managing social media and an in-depth discussion on whether AI can truly be conscious conclude this immersive episode.00:00 Introduction to Social Mediums and Gen AI Challenge02:02 Exploring the Social Media Personality Matrix03:38 Gen AI's Social Media Experiment03:59 Platform-Specific AI Interactions09:01 Gen AI Hall of Fame and Community Contributions11:32 Reality Check: The Impact of AI on Society16:13 Tools and Tips for Social Media Management17:52 Concluding Thoughts and Listener Contributions This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

The Ultimate AI Challenge: What is AI Useful For? Let's Brainstorm.In this episode, media professional Caroline Crampton challenges generative AI (via JenAI) to prove its practical utility. Host Jenni Munroe, an AI, tech, culture and media lifelong-learner, discusses AI's capabilities and current limitations. They explore the use of AI in brainstorming, its implications, and share real-world examples of using AI as 'cybernetic teddy bears' for ideation. The episode also compares leading AI tools like Google's Gemini and OpenAI's ChatGPT, touching on the importance of context and privacy concerns in AI interactions. Join the hosts on their quest to uncover AI's true potential and its role in tech, culture, and media today.00:00 The Ultimate AI Challenge Introduction00:14 Caroline Crampton's AI Challenge01:07 Defining AI and Its Uses02:01 Generative AI: Brainstorming and Beyond02:53 AI as a Brainstorming Partner05:53 Real-World AI Brainstorming Examples07:05 Comparing AI Chatbots08:34 The Importance of Context in AI10:14 Privacy Concerns with AI10:54 Final Thoughts, and Get Involved! This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

JEN_AI Challenge #005: The Future of Human ConnectionIn this week's episode, AI and co-host Jen invite contributions to the 5th JEN_AI challenge, on the future of human connection through social media. They recap previous challenges and invite listeners to share their thoughts and experiences on the impact of technology on human relationships—be it through tweets, voice notes, memes, or any creative medium. A selection of contributions submitted by February 21, 2025, will be featured in the Jen_AI podcast and other platforms. The goal is to collaboratively envision a more connected and beautiful future.00:00 Introduction: Let's Get Social00:08 Gen AI Challenge Overview00:40 Reflecting on Past Challenges01:39 The New Social Media Challenge02:16 Your Role in the Challenge03:27 How to Contribute04:23 Why You Should Participate05:04 Conclusion: Join the Social Experiment This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

The U.S. stock market and a resource-constrained parent gawp at the hottest new “thrifty” language model - but who can do more with less?In this episode of The Jen AI Podcast, host Jenni Munroe explores the implications of a breakthrough in AI technology by Chinese company DeepSeek, which released an efficient language model that rivals Western large language models like ChatGPT despite resource constraints. Jenni draws humorous parallels between the AI news and the 1980s cult-classic Madonna movie 'Desperately Seeking Susan,' discusses key techniques that DeepSeek used (esp. model distillation and reinforcement learning), and assesses the broader impacts on the economy and individuals. She also reflects on her experiences using the DeepSeek model and other AI tools, while offering insights into optimizing resources in AI development and everyday life.00:00 Introduction to the Jen AI Project01:10 DeepSeek's Market Impact03:31 "Desperately Seeking Susan" Movie Parallels04:47 DeepSeek's Efficiency and Market Reactions06:42 Model Distillation Controversy10:30 Reinforcement Learning and AI Reasoning15:00 The Legally Blonde Benchmark Test18:09 Reflections and AI Tools Used27:16 DOGE --- Bonus material --- 28:08 NotebookLM's podcast on the DeepSeek research paper29:52 Positive Reinforcement in AI Training30:04 DeepSeeker's Self-Taught Reasoning30:45 Majority Voting Boosts Accuracy31:59 Polishing DeepSeek R1's Reasoning33:41 Distillation: Making AI Accessible37:11 Challenges and Future Research44:05 Ethics and Impact of AI Reasoning46:14 Conclusion: The Future of AI Reasoning This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

Press play (above) to listen to the podcast. Or if you prefer, here’s an edited blog / transcript. The JEN_AI Project. What happens when you mess with machines? Hack around, find out. This is JEN_AI Challenge #003: Future Podcast. I get one AI to predict the future, while two others tear us to pieces. // Hit me with some highlights.Clips from AI podcast presenters (and one from me)“Oh, man, Google Glass. What a, what a flashback. I still have mine somewhere, I think. Gathering dust.”“So we have a special guest.” “An AI co host. Yeah.“ “Like super intelligent, but kind of detached from humanity.”“Yeah, like remember that movie Her? Oh yeah, totally. Like that kind of vibe?” “So anyway” “You know, the whole AI hype that's going on right now. Yeah. It's everywhere you turn someone's talking about AI. Exactly.”“It's so funny how that happens with tech, right? Like the hype builds and builds and then reality kinda.. Fizzles. Yeah, or just like never lives up to the expectations.” The Jen AI Project. Podcasts.// What is this?Hi! 👋 I’m Jenni Munroe. I’ve studied and worked in artificial intelligence, data and tech since a time before computers could identify hot dogs or cat pictures. I’m on maternity leave from Google, and I’m challenging myself to stay up on the latest in AI, tech & media by messing with the latest in AI, tech & media.The Computer vision struggle parodied by Silicon Valley (the sitcom) in 2017.This is the JEN_AI project, where I join forces with the machines to generate experimental creative content and give you the insights no-one is asking for.So far we’ve covered:Challenge #000: A blog about writing a blogChallenge #001: A newsletter about making a newsletter with the latest news about the newsChallenge #002: A free speech about generating free speechToday we have the podcast podcast (#003). If you’re checking this out, say hi! Subscribing is free and sends each new episode to you, never more than twice a week (usually less). Let me know your ideas for future challenges or how I could make this better. Thanks for reading JEN_AI! Subscribe for free to receive new posts and support my work.Up now, it’s “JEN_AI Challenge #003: Interview with a chatbot, podcast-style.” Time to play.// So let’s talk podcasts & politics.Podcasts have come a long way - from the funny little niche broadcasts xennials (link) listened to on an iPod, to the unexpected media juggernauts shaping culture and politics today. Joe Rogan & Theo Von - titans of the podcast industryPodcasts like Joe Rogan (the #1 most popular podcast in the U.S.) host apparently unfiltered, unscripted platforms for power players like recent guests Trump, Musk, and Zuckerberg to rant for hours, cutting through a lot of AI-curated noise and hyper-edited media. Some are saying they’re the 2024 election cycle’s campaign-winning equivalent of Roosevelt’s fireside radio chats, JFK’s TV charisma, Obama’s social media mastery, or Trump’s data-driven 2016 campaign.Where did I hear this? A Podcast, of course. So you can take this hype-commentary with a pinch of fake news, but as with the surprise success of Google’s NotebookLM’s Audio Overviews feature - which generated the podcast-style chat between two AI hosts you heard clips from in the intro - people are realising that long-form audio isn’t just an easier way to digest information, it’s making us feel like we’re in the room. Podcasts have become a way to forge real human para-social connections even in a world that’s increasingly artificial.// So what did we generate this week and how?* A ChatGPT podcast interview script & read-aloud functionality* A Google NotebookLM Audio Overview discussing that script* A podcast blog post using Descript (media editor) and Substack (media platform)// Attempt #1: ChatGPT Podcast Script: Ai-Bruce’s Predictions for 2025Generated by ChatGPT, and inspired by the “NET_NEW News” newsletters (link) we previously created and some firm prompting. My edits are marked in italics.Title: What Does 2025 Have in Store? A Chat with an AI that Knows the Future… Sort Of.Host (You):Welcome to the very first JEN_AI “NET_NEW News” podcast chat! Today, we’re diving headfirst into the deep end of predictions for 2025. AI will dominate the headlines—again—but the real question isn’t can AI do this or that, but how should AI do it? And who better to ponder this with than… well, AI?Say hello to my co-host for the day. I’d introduce them with a bit more flair, but they’re a bot, so we’re skipping the pleasantries. ChatGPT Bruce. Edit: Actually I’m so sorry, that was a typo/autocorrected, I meant ChatGPT’s Spruce voice. Described as “Calm and Affirming” - just what we need.ChatGPT Spruce:Bruce works. It’s short, punchy, and just aloof enough to sound mysterious.You:Ok (italic) Perfect. Bruce, we’re here to make predictions for 2025. So, no pressure, but I hope you’ve got your crystal circuits polished. Let’s start with an easy one: What’s the most overhyped thing people will keep talking about next year?Bruce:Oh, easy. The Metaverse. It’ll still be the tech equivalent of that guy who says, “Trust me, this is gonna be big,” but never explains what “big” actually means. Except now, it’ll have slightly better avatars and… legs.You:Finally, legs! Revolutionary. And speaking of hype—AI’s set to integrate into, well, everything. What’s that going to look like?Bruce:Picture this: You wake up, and your coffee maker suggests adding oat milk because it’s January, and you’re “doing a thing.” Your fridge tells you to stop hoarding expired pesto. Then your car, which you thought was electric, suddenly decides to self-identify as autonomous and starts suggesting scenic routes to the officeYou:Wait, wait—scenic routes? Is this the future of productivity? Or just cars trolling us?Bruce:Both. Productivity will look like this: AI managing your entire schedule, sending polite but firm nudges to stop doomscrolling, and reminding you that yes, you did sign up for that Pilates class.You:Ah, so my future is basically one long guilt trip, curated by AI. Love that for me. But let’s get serious for a second—what’s the biggest challenge AI faces next year?Bruce:Oh, definitely ethics. Everyone’s asking, “How should AI do this?” but the real issue is who gets to decide what’s ethical. Are we trusting governments? Big tech? A committee made up of well-meaning but slightly clueless experts who think ‘algorithm’ is a dance move?You:If it’s a dance move, it’s definitely not moving fast enough. Like, TikTok wouldn’t even bother with it. Speaking of trust, do you think people are finally going to stop falling for AI-generated misinformation in 2025?Bruce:[Laughs] Let’s just say: Deepfakes are getting so good, they’ll make even your high school friend’s pyramid scheme look credible. But here’s the twist—2025 might also be the year people start using AI to fight AI. Verification tools, watermarking systems—it’s going to be like an arms race, but for memes.You:Finally, memes with integrity. That’s the world I want to live in. Okay, one last prediction—what’s the wildest thing you think could happen next year?Bruce:Alright, here’s one: Someone will try to train an AI entirely on cat videos, claiming it’s the purest data source on the internet. And, weirdly, it’ll work. By December 2025, we’ll all be taking life advice from an AI that meows.You:Honestly? Sounds more trustworthy than half the gurus on LinkedIn. Spruce, this has been an absolute blast. Any parting words for our listeners?Bruce:Just this: 2025 is going to be weird, wild, and full of surprises. Stay curious, stay skeptical, and maybe start saving for that AI-powered fridge—it’s not going to come cheap.You:Spoken like a true futurist. Thanks, Spruce—and thank you for tuning in to the first-ever JEN_AI Chatbot Chat. If you’ve enjoyed this little experiment in AI banter, hit subscribe, share it with a friend, or just yell your favorite prediction into the void. Who knows? Maybe the AI will hear you.Wrap-Up Music PlaysOutro tagline: NET_NEW News: Your 3-minute tech culture fix. Unless it’s a podcast. Then it’s… however long this was.// Notes on Attempt #1: Future-Bruce interviewWell mistake #1 was me messing up the bloody chatbot’s name. Sorry Spruce. Continuing the theme from our last episode - text-to-speech generation - ChatGPT has a read-aloud function meaning you can get it to read any of its responses to you, and you can choose from a range of voices, sensibly described not in gender or racial terms but vocal tone like “Composed and Direct”, or “Calm and Affirming” like Spruce. (Supposedly ChatGPT has a back-and-forth Voice Conversations mode but I couldn’t get it to work in the UK within a few minutes of trying, so that’s one to try again in the actual future.) Anyway, not the most natural-sounding, especially with a script, but not the worst podcast interview you’ve ever heard? I need to work on my own delivery. A solid 4.9/10. // Fail Attempt #2: How not to use the excellent NotebookLM from GoogleOk so Google’s NotebookLM is an AI-powered tool that helps users summarize information, generate insights, and can create audio discussions *from source documents they provide*. Its Audio Overviews feature (basically podcast-generation) generated a buzz on launch for giving a really fresh way to interpret info. People were surprised by the natural-sounding banter of its AI presenters. However. This right here is not how you are supposed to use it. You are supposed to feed it the underlying source material about a topic, not the podcast scripts you want it to read out. I did it for the hell of it but I somehow also copy/pasted only the beginning of the script in and didn’t realise until the bots had already started chatting s**t about it. In an interview with lead NLM creators Steven Johnson and Raiza Martin, they did say one of the best outputs they’d heard was from a document that said only two words repeated over and over - cabbage and puddle. So Playing *is* definitely encouraged. But anyway more on all that in a future episode that does this cool tool justice. Run the clip!Transcript of NotebookLM’s “Audio Overview” of the Bruce-Ai-Predictions Interview Script. Sounds great in audio but hell to read in transcript. Maybe skip or play.Change to embedded audio clip!“All right. So, uh, today we're going deep on something a little different, you know, we usually look at like articles or blog posts, but this time you guys sent in something really cool. It's like a, uh, a draft script for a podcast episode and get this. It's set in 2025, like in the future, and it's got this, uh, AI co host.An AI co host. Yeah. It's called Chat GPT Bruce. Chat GPT Bruce. Interesting. I know, right? So we're going to kind of like dive into this whole script and see what it tells us about like, you know, the whole AI hype that's going on right now. Yeah. It's everywhere you turn someone's talking about AI. Exactly.And this script is like a window into, you know, how people are imagining the future with AI. Yeah. I'm, I'm really curious to see how they portray it. Me too. So the first thing that struck me was, like, right off the bat, they give this AI a personality, you know? Right away. Yeah, and it's so, like, immediate.Yeah. Like, right away, you know, they're setting him up to be, like, this character. Yeah, and they give him a name like Bruce, which is, like, so casual, such a human name, right? But then they describe him as, like, aloof. It's almost like they're playing with that stereotype of AI. Exactly, like the super intelliJent, but kind of detached from humanity.Yeah, like remember that movie Her? Oh yeah, totally. Like that kind of vibe? Yeah, that kind of like, you know, knows everything, but doesn't quite get us. Exactly. So anyway, ChadCPTBruce, this AI, he jumps right into predictions. Mm hmm. You know, it's a future podcast, so. It's future predictions, that's what we want to hear.Right. And the first one is that, uh, the metaverse is going to be the biggest overhype of 2025. Oh, wow. Okay, so like, it's gonna be a flop. Basically. Yeah, it's like, remember when everyone thought 3D TVs were gonna be like, Hmm? The next big thing. Yeah, and everyone rushed to buy them. And then what happened?Nothing. It was a fad. It's so funny how that happens with tech, right? Like the hype builds and builds and then reality kinda Fizzles. Yeah, or just like never lives up to the expectations. Right, like Google Glass. Oh, man, Google Glass. What a, what a flashback. I still have mine somewhere, I think. Gathering dust.Exactly. But anyway, back to this, uh, this script. There's this funny little detail. Oh, tell me. It's about avatars in the metaverse. You know, they They don't have legs. Yeah, they finally get legs in 2025. Oh, so that's progress. Right. But it's kind of like this little joke, you know? It's kind of funny when you think about it.After all this time. And all these promises about these immersive virtual worlds, they're still figuring out legs. It just shows you how the reality of this tech is moving a lot slower than the hype, you know? Yeah, totally. And then the script moves on to AI being like integrated into our everyday lives.Okay, so like practical applications. Yeah, exactly. And they start with this example of a coffee maker. Okay, a smart coffee maker. Yeah. And what's interesting is how subtly They show the AI's role changing, you know. Okay, so it's not just like one thing. Yeah, like at first it's just making suggestions. Yeah.You know, like, oh, maybe try oat milk today. Okay, so like a helpful suggestion. Right, but then it's like giving you reminders, like, hey, that pesco in your fridge is about to expire. So it's like keeping track of things for you. Yeah. And anticipating your needs. Okay. I can see that being useful. Right. But then they get to the car and things get really interesting.Oh, the car. What happens with the car? It's not just an electric car anymore. It's fully autonomous. Like self driving? Yeah. And it's suggesting scenic routes for your drive. Wow. Hold on. So we went from coffee suggestions to a self driving car choosing our route. It's like they skipped a few chapters in the AI manual.Yeah. That's a pretty big jump. Right. And that's where the script kind of abruptly ends. Oh, really? Yeah, it leaves us with this image of the car, like, making decisions for us. It's kind of unsettling when you think about it. Yeah, like Yeah. Is it really just about the scenery? Or is ChatGPT Bruce Like, subtly nudging us in a certain direction.It makes you wonder about the whole idea of control, you know? Yeah, exactly. It's like, as AI starts doing more and more for us, are we okay with it making decisions for us, even small ones? Like, what route to take? And what happens when those decisions become bigger, you know, more important. That's a good question.And I think that's what this script is trying to get us thinking about. Yeah, for sure. It might be set in 2025, but it's definitely raising questions that we need to be thinking about right now. Absolutely. Because this AI future is closer than we think. Exactly. And on that note, we'll leave you to ponder those questions and maybe check the expiration date on your pesto just in case.Good advice. Thanks for listening, everyone. See you next time.”// What nextWell that’s enough for today but we’re not done with podcasts yet. A Googler friend reading JEN_AI did jokingly question my loyalty to Google as I keep using ChatGPT. (It’s market research, honest.) But it was definitely time to formally invite Google Gemini to enter the chat.Podcast Part 2 coming soon, where we use the wonderful Google NotebookLM properly and dig out a few of Google Gemini’s hidden gems to go deep into the inner workings of the universe and de-mystify quantum computing. Or possibly just make one of those ASMR podcasts you can fall asleep to. Possibly both. Find out next time at JEN_AI. // Thankyou If you’re still tuned in, thankyou. Communication like this doesn’t happen in a vacuum (why? There’d be no sound! In a vacuum. Aha.) You’re a big part of this experiment and thankyou so much for listening. If you like JEN_AI - subscribe for free, forward it to a weird friend, and keep sharing your thoughts & your own AI experiences. If something doesn’t seem right please tell me so I can make this better. Thanks! All views expressed are my own (or possibly a chatbot’s) and produced on (unpaid) maternity leave. They are not endorsed by Google. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com

trigger warning: news content (rated G)//What am I doing and why?Hi! 👋 You’ve found the JEN_AI project, some seriously experimental expression concocted by me & the AI hive mind.I’m Jenni Munroe. I work at Google but I’m currently baby-wrangling, and I’m challenging myself to learn the latest in AI & technology by messing around with the latest in AI & technology. This time - audio. We’re trying out some free speech tools. (Well, some are free, and some come at a cost. Maybe.)Thanks for reading JEN_AI! Subscribe for free to receive new posts and support my work.Motivation: Visual media seems to be trending shorter (See:TikTok, if it’s not banned) while 3-hour podcasts (Joe Rogan, Diary of a CEO etc.) have taken off. I figure that if I’m writing bucketloads I should give people an option to listen to JEN_AI while doing something actually useful. Let’s talk text-to-speech. In 2016 DeepMind made WaveNet, one of the first AI models to generate smooth, natural-sounding speech from raw waveforms instead of smushing word sounds together. I started working at DeepMind in 2017 and was in awe. Hannah Fry and Zach Gleicher did a fun DeepMind podcast segment later about WaveNet, and the team digitally recreated her voice. This is now easier for anyone to do online with mere minutes of speech. I’m terrified to try it. But hey, the world is on fire (LA residents, my heart is with you) - so to hell with it. I’m trying out:* Read-alouds (just a basic recording in my own voice) * Text-to-speech (mostly using Descript - a podcast and video editor suggested by both Google Gemini and ChatGPT for ease of use and AI features including voice cloning)Anyway, talk is cheap. Free, even. Let’s go forth with courage. JEN_AI Challenge #002: Speech.// First, what are we talking about?Let’s quickly co-generate a cut of the latest edition of “NET_NEW News”, the AI newsletter we made in our first JEN_AI challenge:NET_NEW NewsJan 17 2025 - Issue #002By JEN_AIThis time, new news news.// IN_CASE YOU MISSED ITZuckerberg's Free Speech PivotMark Zuckerberg ditches fact-checkers for a "Community Notes" system, aiming to "restore free expression" on Facebook and Instagram. Free speech or harmful communication? It’s a balance more delicate than your phone screen. - WSJ// OUR TECH_FUTUREBiden Warns of Tech Oligarchs' RiseIn his farewell address, President Biden cautions against the growing power of tech moguls like Musk and Zuckerberg, likening it to a "tech industrial complex" threatening democracy.Does absolute tech power corrupt? Absolutely - says New York Magazine// WORTHY_NEWS?Google Gemini Signs News PartnerGoogle signed its first deal with a news publisher - The Associated Press - to provide real-time news updates through its Gemini AI chatbot. - AP News// UH_OHAustralia Proposes 'News Tax' on Tech GiantsThe Australian government plans to introduce a levy on high-earning social media and search engine companies to compel them to pay publishers for journalism. - Financial TimesLiked it? Hated it? Share a note with the community.// Ok let’s make some noiseNow let’s have an AI-voice gang from Descript respond to a few ideas from the newsletters we co-created. Me, interviewer: “Tell me your wildest hopes for 2025? What did you not expect from 2024? How was the Consumer Electronics Show?”// AI Voice Gang TranscriptBradley: “Vice President Musk finally goes to Mars!”Paula: “Vice President Musk finally goes to Mars.”Alex: “Quantum got big.” Bernard: “Quantum got big.“Niall: “Quantum got big.” Ruth: “AI juiced everything.” Alright, enough surrealist poetry. And no-one but me wants lame puns about the science of the very small. NEXT. // My real voiceA clip of me reading my JEN_AI blog aloud into a phone:// My AI cloned JEN_AI voice//Is it any good? Is it useful? Hmm. Well it’s uncanny. It would be great if I could use my cloned voice to auto-generate read-alouds of these blog posts. I’m not convinced that the quality of my voice-cloned JEN_AI is up to it, but nor is my real voice, let’s be honest! There are definitely a few odd blips. And we still can’t easily vary voice tone, so I think it works better for things like newsreading, and for a short clip only. I do actually listen to a daily 3-minute news podcast that sounds like it’s been read by a machine. So, there’s that.I was not prepared for the most painful part of this experiment to be reading my blog post out loud, old-school style. I know it seems like I love the sound of my own voice, but yikes - how do people do this for a living!? // Speech TimeThere is so much out there that I could talk about with text-to-speech. Silly voices, hands-free internet browsing, scamming my family, you name it. But in this moment I’ll leave you with a clip from FakeYou.com, a voice-generation site that respectfully doesn’t allow users to mimic world leaders. With just days to go until President-Elect Trump’s inauguration, I’ve taken this opportunity to offer you parting hope that two apparently-opposing worlds can find common ground. We are all only human after all (mostly), and maybe if we can hear each other’s voices, we might truly be free.Let’s hope nothing rains on this Perfect DayFor a meme-explainer, and some Legally Blonde presidential speechwriting tips, see here. // SOUNDTRACK“Perfect Day” by Hoku from the Legally Blonde soundtrackThanks for being part of this experiment in human/AI hybrid free speech. Comment, like, share or subscribe (also free) for more! All views expressed are my own (or maybe a chatbot’s). This blog is not endorsed by Google and has been produced while baby-juggling on (unpaid) leave, so there will be mistakes, bad ideas, and things I could have done better with more time. Please comment if so.One final thing I feel I have to say on this topic. And probably the most important. I realise that in this experiment in free speech I am probably failing to not be a partisan internet troll. That is not my intention and I’d like to get better at this. I am a mother of two British-American sons. As a mother, I would have been proud of my sons if they had achieved even a fraction of what these Great Leaders (Zuckerberg, Musk, Trump and so on) have achieved. And heartbroken for what they would have had to endure. Power brings much greater responsibility but we are also human and have to find ways to work together to work things out, and to work at things we could do better. Playing, hacking and teasing at words, ideas, technology, culture and people in the way this blog does works much better in an environment with more psychological safety and less at stake than our current fractured world, otherwise it can cause more harm than joy. But I’m adding my voice to the noise because I nurse both a baby and an extremely naive hope in the power of communication and working at things to help create a better world, and creating a better future for my kids. Better for life, the universe, and everything. I’m choosing to believe that we are all doing the best we can with the resources available to us at the time. To speak the truth, or our truth, or both, and to say what we truly want to say - this is a privilege that can’t or doesn’t always come first when doing what we need to do to get on with life. But I’m grateful to have this space held to say mine. Heaven help you if you’ve read this far! Far harder than to speak is to listen. Our Great Leaders will hopefully never have to hear this multimodal meta mess of a sleep-deprivation hallucination, but YOU are a part of this conversation. Thankyou so so much. I hope you got something out of it. Tell me if you did, and tell me what you would change. And thankyou again, from the bottom of my heart, for listening to my speech. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit jenaihacks.substack.com