How Do You Use ChatGPT?

The NYT’s Kevin Roose has 18 new friends—none of whom are human.

His new friends are AI personas that he made with Noma, Kindroid, and other AI companion apps. There’s fitness guru Jared, therapist Peter, trial lawyer Anna, and over a dozen more.

Kevin talked to them every day for a month, sharing his feelings, asking for parenting advice, and even using them for “fit” checks.

This isn’t the first time Kevin has had an…unusual interaction with an AI persona. A year ago, he was the target of Bing’s chatbot Sydney’s unhinged romantic affections.

Kevin has gone deeper into the world of AI companions than anyone I know. He is a tech columnist at the New York Times, cohost of the Hard Fork podcast, and the author of three books. In this episode, I sat down with Kevin to learn more about his interactions with AI. We dive into:

• Why AI companions aren’t just for lonely people or shy teenagers
• Why AI personas are better friends than ChatGPT
• How AI companions can be used to safely explore different social contexts
• The risk of young people relying on AI for friendship
• The icks of AI dating and intimacy
• How to use AI to articulate what you value in your relationships

This is a must-watch for anyone curious about how AI is changing the way we form relationships.

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT here. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every
• Follow him on X

Links to resources mentioned in the episode:

• Kevin Roose
• Hardfork, the podcast that Kevin cohosts
• Kevin’s latest book about being human in a world designed for machines
• Kevin’s piece in the New York Times about his experience making AI friends
• Two of the apps that Kevin used to create AI companions: Kindroid and Nomi
• Dan’s piece that explains why AI writing will feel real through psychologist D.W. Winnicott’s theory
• Every’s piece that explores AI companion app Replika

Nick Dobos, maker of the #1 programming GPT, on prompt-gramming with AI

Nick Dobos showed me how to ship a website with two words and a single click.

He’s the creator of Grimoire, the #1 custom GPT for programming that has been used for over 1 million chats.

All he gave Grimoire was two words: “coffee website.” Just a minute later, Grimoire built the website and pushed it live to the internet. It was wild.

Grimoire can do a lot more than create websites—it’s a coding assistant with 75+ built-in hotkey commands and sample projects, a guide to learning how to code from scratch, and a tool for programmers to find answers to their questions in real-time.

Before he created Grimoire, Nick was an iOS developer at Twitter. When ChatGPT came out, Nick started experimenting with it—and ended up building Grimoire. Today, he’s at the leading edge of experimenting and building with AI.

I sat down with Nick to explore how people are using Grimoire and what it tells us about the age of programming by prompting. We dive into:

• How AI is massively lowering the barriers to code

• Why it’s important to solve the “blank canvas problem” that people experience while creating with AI

• How AI tools can streamline your creative process

• Why Grimoire has an edge over ordinary ChatGPT

• The best ways to use Grimoire to code smarter and faster

This is a must-watch for coders, creative people, and anyone curious about how AI is changing the way we interact with computers.

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe

• Follow him on X: https://twitter.com/danshipper

Timestamps:

1. Introduction: 00:00:31

2. How Nick built Grimoire, the top-ranked GPT for programming: 00:05:20

3. Ship a website with two words and a single click: 00:10:25

4. How Grimoire is solving the “blank canvas problem” in AI creation: 00:14:57

5. The coding curriculum that can take you from zero to full programmer: 00:16:30

6. Why Grimoire has an edge over ordinary ChatGPT: 00:23:29

7. Nick’s thoughts on building the system prompt for a GPT: 00:34:10

8. The utility of AI as a new layer on top of existing apps: 00:40:04

9. How Nick uses a custom GPT to unpack his emotions: 00:43:11

10. How to use AI to break down tasks—from programming to daily to-do lists: 00:50:35

Links to resources mentioned in the episode:

• Nick Dobos: @NickADobos

• Grimoire: https://chat.openai.com/g/g-n7Rs0IK86-grimoire

• Nick’s website for his experiments with AI: https://mindgoblinstudios.com/

• AI-first code editor Cursor: https://cursor.sh/

• Open Interpreter: https://www.openinterpreter.com/

• Lisa Feldman Barrett’s book: How Emotions Are Made

• Demo Hume, the empathetic AI voice: https://demo.hume.ai/

This AI can read emotions better than you can.

It was created by Alan Cowen, the cofounder and CEO of Hume, an AI research lab developing models that can read your face and your voice with uncanny accuracy. Before starting Hume, Alan helped set up Google’s research into affective computing and has a Ph.D. in computational psychology from Berkely.

Hume’s ultimate goal is to build AI models that can optimize for human well-being, and in this episode I sat down with Alan to understand how that might be possible.

We get into:

• What an emotion actually is

• Why traditional psychological theories of emotion are inadequate

• How Hume is able to model human emotions

• How Hume's API enables developers to build empathetic voice interfaces

• Applications of the model in customer service, gaming, and therapy

• Why Hume is designed to optimize for human well-being instead of engagement

• The ethical concerns around creating an AI that can interpret human emotions

• The future of psychology as a science

This is a must-watch for anyone interested in the science of emotion and the future of human-AI interactions.

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe

• Follow him on X: https://twitter.com/danshipper

Timestamps:

1. Dan tells Hume’s empathetic AI model a secret: 00:00:00

2. Introduction: 00:01:13

3. What traditional psychology tells us about emotions: 00:10:17

4. Alan’s radical approach to studying human emotion: 00:13:46

5. Methods that Hume’s AI model uses to understand emotion: 00:16:46

6. How the model accounts for individual differences: 00:21:08

7. Dan’s pet theory on why it’s been hard to make progress in psychology: 00:27:19

8. The ways in which Alan thinks Hume can be used: 00:38:12

9. How Alan is thinking about the API v. consumer product question: 00:41:22

10. Ethical concerns around developing AI that can interpret human emotion: 00:44:42

Links to resources mentioned in the episode:

• Alan Cowen: @AlanCowen
• Hume: @hume_AI; hume.ai
• If you want to demo Hume: demo.hume.ai
• The nonprofit associated with Hume: Hume Initiative
• Lisa Feldman Barrett’s book: How Emotions Are Made
• The TV series based on Paul Ekman’s theory of emotion: Lie to Me

Learn how to use philosophy to run your business more effectively.

Reid Hoffman thinks a masters in philosophy will help you run your business better than an MBA.

Reid is a founder, investor, podcaster, and author. But before he did any of these things, he studied philosophy—and it changed the way he thinks.

Studying philosophy trains you to think deeply about truth, human nature, and the meaning of life. It helps you see the big picture and reason through complex problems—invaluable skills for founders grappling with existential questions about their business.

I usually bring guests onto my podcast to discuss the actionable ways in which people have incorporated ChatGPT into their lives. But this episode is different.

I sat down with Reid to tackle a deeper question: How is AI changing what it means to be human?

It was honestly one of the most meaningful shows I’ve recorded yet. We dive into:

• How philosophy prepares you to be a better founder
• The importance of interdisciplinary thinking
• Essentialism v. nominalism in the context of AI
• How language models are evolving to be more “essentialist”
• The co-evolution of humans and technology

Reid also shares actionable uses of ChatGPT for people who want to think more clearly, like:

• Input your argument and ask ChatGPT for alternative perspectives
• Generate custom explanations of complex ideas
• Leverage ChatGPT as an on-demand research assistant

This episode is a must-watch for anyone curious about some of the bigger questions prompted by the rapid development of AI.

Thanks again to our sponsor CommandBar, the first AI user assistance platform, for helping make this video possible. https://www.commandbar.com/copilot/

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe
• Follow him on X: https://twitter.com/danshipper

Links to resources mentioned in the episode:

Reid Hoffman: @reidhoffman

The podcasts that Reid hosts: Possible (possible.fm) and Masters of Scale (https://mastersofscale.com/)

Reid’s book: Impromptu

The book Reid recommends if you want to be more philosophically inclined: Gödel, Escher, Bach

Reid’s article in the Atlantic: "Technology Makes Us More Human"

The book about why psychology literature is wrong: The WEIRDest People in the World by Joseph Henrich

The book about how culture is driving human evolution: The Secrets of Our Success by Joseph Henrich

Seth-Stephens Davidowitz wrote a book in 30 days—and he did it with ChatGPT.

Seth is a data scientist, economist, and author who challenged himself to write a book—Who Makes the NBA?—in less than 1 month after realizing how fast he could work by using ChatGPT plugin Advanced Data Analysis.

But along the way he discovered something else: Writing with AI wasn’t just faster, it was also way more fun.

Seth outsourced the boring parts of data analysis—like cleaning data, merging files, and looking up code snippets—to AI. This left him to focus on what he loves: thinking up questions to ask the dataset.

In a world where AI can answer any question humans know the answer to, asking the right questions is becoming increasingly important—a skill Seth isn’t just really good at, but also finds joy in.

In this episode, Seth walks me through how he used AI to analyze data and write a book in 30 days. We get into:

• How to create and edit complex charts with AI in seconds
• Using ChatGPT to brainstorm creative ideas
• How AI is redefining who can be an artist
• Why ChatGPT is an excellent tool to get a quick ballpark estimate
• Developing a sixth sense about when ChatGPT is wrong
• The power of AI instantly answering hard questions that would normally take months of research

We also use ChatGPT to analyze a dataset of Olympic athletes live on the show—in pursuit of finding out which sport I’m best suited for!

This episode is a must-watch for anyone curious about data science and how AI is transforming the future of creativity (or who is just a fan of the NBA).

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every
• Follow him on X

Links to resources mentioned in the episode:

Seth Stephens-Davidowitz: https://twitter.com/SethS_D http://sethsd.com

Seth’s books: Who Makes the NBA? , Everybody Lies and Don’t Trust Your Gut

Nicholas Thorne is building Squarespace for the AI age. It’s called Audos, and it’s an AI chatbot to help any entrepreneur go from idea to:

- Pitch deck

- Working website

- Custom GPT

- User interviews with real customers

All in just a few minutes. And he did it using ChatGPTapp. It’s AI all the way down—and it’s one of the most impressive AI businesses I’ve ever seen.

Nicholas is a general partner at Prehype, an incubator that launched Barkbox and Ro Health. It’s also where I started Every, so it was great to come full circle.

Nicholas’s job at Prehype is to launch new companies. He’s taken everything he’s learned running an incubator and used it to help entrepreneurs start businesses at scale—with AI.

As we talk, Nicholas walks me through the interactions of Audos’s chatbot with a user live on the show.

Nicholas tells me that he used ChatGPT to prototype most of Audos’s features—despite being non-technical himself. He shares exactly how he did this by showing me how he’s using AI to create a new feature for the product. We get into: - Ways AI can make you a more effective founder - How to use ChatGPT to build your prototype - Strategies to refine problem statements with AI - Using GPTs to gather and synthesize customer feedback This episode is a must-watch for anyone who has ever toyed with the idea of starting a business—and wants to do it with AI.If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ⁠ultimate guide to prompting ChatGPT⁠. It’s usually only for paying subscribers, but you can get it here for free: https://every.ck.page/ultimate-guide-to-prompting-chatgpt To hear more from Dan Shipper: Subscribe to Every: ⁠https://every.to/subscribe⁠ Follow him on X: ⁠https://twitter.com/danshipper⁠ Timestamps: 00:00:00 - Teaser 00:00:48 - Introduction 00:12:10 - How AI can make you a more effective founder 00:17:03 - Live demo of Audos! 00:24:07 - Why Nicholas built an AI tool to enable entrepreneurs 00:25:35 - How Audos puts you in “edit mode” instead of “create mode” 00:28:12 - Tools to gather customer feedback, generated by Audos 00:32:58 - How Audos actually works 00:35:07 - Nicholas uses ChatGPT to prototype a new feature 00:42:37 - How to establish checks and balances while using ChatGPT 00:57:20 - AI as a force for pushing entrepreneurship to new heights Links to resources mentioned in the episode: Nicholas Thorne: ⁠@thorneny⁠; ⁠[email protected]⁠ Audos: ⁠https://www.audos.com/⁠ Nicholas’s book, Me, My Customer, and AI, is slated to publish next month. Follow him on X for updates: https://mmcai.super.site/

Antidepressants changed my life.

I have OCD and antidepressants did what nearly a decade of therapy, meditation, and supplements couldn’t: they allowed me to live my life without being in a 24/7 spiral. (Bonus: they actually made therapy and meditation far more helpful once they started to work.)

I think antidepressants are seriously misunderstood. Yes, they blunt negative emotions. But they also operate on personality and sense of self: they can make you bolder, less sensitive to failure, and less risk-averse.

In short: they are a technology that changes how we see ourselves and the world.

That’s why I invited Dr. Peter D. Kramer on my show. Dr. Kramer is a psychiatrist and the author of eight books, including Listening to Prozac, which is an international bestseller. He has practiced psychiatry and taught psychotherapy at Brown University for nearly four decades.

Listening To Prozac is one of my favorite books, and it documents Dr. Kramer’s experiences as a psychiatrist seeing how antidepressants like Prozac changed his patients’ sense of self and personality.

Now, you might be wondering why have him on a show about ChatGPT? Well, technology can change who we are even if it comes as a software product rather than a pill. It’s undoubtedly true that as generations of humans learn to live with AI, it will change what it means to be human—and how we see ourselves and the world. I think that can be a good thing, but it could also be scary.

I wanted to talk to Dr. Kramer about his book, and see if we could apply some of his insights in Prozac to ChatGPT. It was an incredible conversation, and I was honored to talk to him.

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe
• Follow him on X: https://twitter.com/danshipper

To learn more about the topics in this episode:

• Listening to Prozac by Peter D. Kramer
• ChatGPT and the Future of the Human Mind by Dan Shipper
• SSRIs by Scott Alexander

Timestamps:

1. Introduction: 00:50
2. How technology changes the way we see ourselves and the world: 08:24
3. Antidepressants and their impact on our personality and sense of self: 21:25
4. How the availability of a technological solution prompts us to see the problem everywhere: 26:35
5. Technology alters the categories we have divided the world into: 34:06
6. How I use ChatGPT in my writing process: 40:05
7. Experimenting with ChatGPT to get relationship advice: 45:41
8. Prompting ChatGPT to be more specific: 51:16
9. Clearly indicate the tone you want ChatGPT to take: 55:11
10. Dr. Peter D. Kramer’s final thoughts on ChatGPT as a therapist: 1:02:27

Links to resources mentioned in the episode:

• Dr. Peter D. Kramer: https://twitter.com/PeterDKramer
• ChatGPT and the Future of the Human Mind by Dan Shipper: https://every.to/chain-of-thought/chatgpt-and-the-future-of-the-human-mind
• Listening to Prozac by Dr. Kramer: https://www.amazon.com/Listening-Prozac-Landmark-Antidepressants-Remaking/dp/0140266712
• Should You Leave? by Dr. Kramer: https://www.amazon.com/Should-You-Leave-Psychiatrist-Autonomy/dp/0140272798
• Against Depression by Dr. Kramer: https://www.amazon.com/Against-Depression-Peter-D-Kramer/dp/0143036963
• Ordinarily Well by Dr. Kramer: https://www.amazon.com/Ordinarily-Well-Antidepressants-Peter-Kramer/dp/0374536961
• Pierre Menard, Author of the Quixote by Jorge Luis Borges: https://raley.english.ucsb.edu/wp-content/Engl10/Pierre-Menard.pdf
• The Soul of A New Machine by Tracy Kidder: https://www.amazon.com/Soul-New-Machine-Tracy-Kidder/dp/0316491977
• Making Hay by Verlyn Klinkenborg: https://www.amazon.com/Making-Hay-Verlyn-Klinkenborg/dp/0941130185
• Oranges by John McPhee: https://www.amazon.com/Oranges-John-McPhee/dp/0374512973

You can build and run a one-person internet business that earns half a million in annual revenue—with AI.

Ben Tossell showed me exactly how in this episode. Ben is the founder of Ben’s Bites—one of the best daily AI newsletters out there, which I love reading every day—and an investor in a number of promising early-stage AI startups. Ben is also an experienced founder whose no-code platform Makerpad was acquired by Zapier.

I think Ben is really good at starting profitable internet businesses that are sneakily big, but don’t require too many resources. Over the last couple of years, he’s assembled a war chest of AI tools including ChatGPT, Claude, Gemini, Lex, and Supernormal to help him do this. In this episode, we get into the weeds of how Ben has integrated AI into his workflow to find new business opportunities, run them well, and evaluate their performance.

We get into:

• How to use ChatGPT as a business strategist
• Building your MVP with ChatGPT
• Turning interview transcripts into compelling articles
• Analyzing business data using AI tools
• How to generate persuasive landing page copy with ChatGPT
• Offload time-consuming tasks to AI

This episode is a must-watch for anyone who is curious about using AI to bootstrap a profitable internet business.

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe

Follow him on X: https://twitter.com/danshipper

Links to resources mentioned in the episode:

Ben Tossell: https://twitter.com/bentossell

I made the greatest trade of my life with Jesse Beyroutey in 2019. We bought Nvidia shares when they were trading at $33. They’re worth nearly $800 today.

I sat down with Jesse to top that trade in 90 minutes using Gemini Pro 1.5’s incredible 1 million token context window—and make a $1,000 trade live on the show.

Jesse is a managing partner at IA Ventures, a $600 million venture fund with seed investments in companies like Wise and Digital Ocean. He’s also a very close friend and one of the smartest people I know.

We unpack our investment thesis for our Nvidia trade and leverage the power of Gemini Pro 1.5 and ChatGPT to orchestrate what we hope will be the best trade of our lives. We put our money where our mouth is and make a $1,000 trade while the cameras are still rolling.

There’s a plot twist at the end of this episode—so stick around to see the epilogue Jesse and I recorded just days after we made our investment.

We get into:

• How Jesse leverages LLMs to get nuanced answers to his questions
• Ways to find patterns in large swaths of data using Gemini Pro 1.5
• Gemini Pro 1.5 and ChatGPT going head-to-head
• How Gemini Pro 1.5 can be used to understand the stock market
• Why it’s important to consistently refine your search queries
• What Jesse thinks are the new big opportunities enabled by LLMs

This is not investment advice, but it’s a must-watch for anyone who wants to leverage the power of AI to make smarter financial decisions.

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe
• Follow him on X: https://twitter.com/danshipper

Timestamps:

1. Introduction: 01:29
2. How Dan made the greatest trade of his life: 03:50
3. Jesse’s strategy to use LLMs to get nuanced answers 05:27
4. Gearing up to orchestrate the best trade of our lives with Gemini Pro 1.5 09:20
5. How Jesse gets AI to make great decisions 17:52
6. Using Gemini Pro 1.5 to find patterns in data 22:38
7. How AI can provide deeper insights into the stock market 26:48
8. Leveraging Gemini Pro 1.5’s huge context window to analyze data 34:41
9. Gemini Pro 1.5 and ChatGPT go head-to-head 46:33
10. Choosing a stock with just 15 minutes left on the clock 1:10:11
11. What Jesse thinks are the biggest new opportunities enabled by LLMs 1:24:01
12. The epilogue Jesse and Dan recorded one week after making the trade 1:28:43

Links to resources mentioned in the episode:

Follow Jesse Beyroutey

Nathan Labenz’s podcast, The Cognitive Revolution

You can break into Hollywood with a movie you made alone in your room.

Dave Clark can show you exactly how in < 60 minutes. He’s a film director with a body of work that includes both feature films and commercials for brands like Google. His latest achievement is a stunning sci-fi short that got Hollywood’s attention, one that Dave made exclusively using AI.

Dave and I make a movie live on this episode, iterating from rough ideas to a real motion picture in < 1 hour. It’s a noir short featuring Nicolas Cage using a haunted roulette ball to resurrect his dead movie career that you don’t want to miss.

We dive deep into the world of AI tools for image and video generation, specifically exploring their implications on lowering the barriers to enter the traditional movie industry. This episode is also packed with Dave’s wisdom on how to use these tools to create mind-bending movies.

We get into:

• How AI is enabling everyone with a laptop to be a filmmaker
• Actionable tips to 10x your use of creative AI tools like Midjourney, Runway, and Elevenlabs
• How to integrate ChatGPT into the process to craft compelling stories
• Strategies to make your AI-generated clips stand out
• How to leverage AI tools to refine your videos

This episode is a must-watch for creative people interested in bringing their stories to life, movie buffs, and anyone curious about the future of creativity.

If you found this episode interesting, please like, subscribe, comment, and share!

Want even more?

Sign up for Every to unlock our ultimate guide to prompting ChatGPT. It’s usually only for paying subscribers, but you can get it here for free.

To hear more from Dan Shipper:

• Subscribe to Every: https://every.to/subscribe
• Follow him on X: https://twitter.com/danshipper

Timestamps:

1. Introduction 01:33
2. How AI is enabling everyone with a laptop to be a filmmaker 10:19
3. The new tool set for making AI films 14:30
4. How to make your AI-generated clips stand out 16:56
5. The first prompt in Dave’s custom text-to-image GPT for our movie 25:00
6. The big advantage text-to-image GPTs have over Midjourney 37:58
7. The best way to generate Midjourney prompts with a GPT 44:13
8. Animating the images for our movie in Runway 49:10
9. First look at our movie! 53:42
10. How Dave thinks about animating images without an obvious motion element 58:22
11. Why you need to be persistent while working with generative AI 59:46

Links to resources mentioned in the episode:

Follow Dave Clark

Borrowing Time, Dave’s viral sci-fi short

Forbes article that mentions Borrowing Time

Dan’s article on how AI is changing filmmaking

Nathan Labenz’s podcast, The Cognitive Revolution