Stay ConnectedThe Every Podcast is Every’s flagship show. Co-hosts Dan Shipper and Natalia Quintero talk with founders, researchers, writers, and operators about what they’re building and how they use AI in their own work. The show also takes you behind the scenes at Every. We share how our team is using and exploring AI, including what we’re trying, what’s working, and what we’re learning along the way.
Formerly known as AI & I.
Read more at every.to.
Copyright: © Dan Shipper
This episode is sponsored by Notion. I’ve been using Notion to manage my professional and personal life for almost 10 years. As a company, they pay attention to the craft and ideas underlying the software they build, and that comes through in the experience of using Notion every day. If you’re a startup, get up to 6 months of Notion Plus with unlimited AI—worth up to $6,000—for free by going to https://ntn.so/every, selecting Every in the drop-down partner list, and using the code EveryXNotion.
Notion cofounder Simon Last told me everything he’s learned from integrating AI into a platform that has over 100 million users.
Simon likes to keep a low profile, even though he’s the driving force behind Notion AI, one of the most widely scaled AI applications in the world.
In his first-ever podcast interview, we get into:
This is a must-watch for anyone interested in building reliable AI products at scale.
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:
Timestamps:
Links to resources mentioned in the episode:
Union Square Ventures is building an AI operating system to support their investment team.
But it’s not what you think: It’s a constellation of AI tools that captures and synthesizes the firm's collective wisdom. It’s evolving every day, and Matt Cynamon is the mad scientist in charge
Matt calls himself a “regular” at USV. In practice that means he’s responsible for running experiments with AI for the firm. As an inherently curious person with the professional obligation to tinker, he’s built a suite of tools for the firm, including:
I sat down with Matt to talk about how AI is enabling him to bring his ideas to life as a generalist, get demos of the tools listed above, and exchange notes on all the other projects he has in the works at USV. We edit actionable insights extracted by an AI from meetings at USV and prepare them to be posted on the firm’s X handle live on the show. We even try out an art project at USV’s office called The Dream Machine, which generates art from conversations. Here’s a link to the episode transcript.
This is a must-watch for anyone interested in riding the AI wave by learning how to ship useful products quickly.
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:
Links to resources mentioned in the episode:
Matt Cynamon: @mattcynamon
Union Square Ventures: @usv, https://www.usv.com/
More about the AI tools at USV: https://www.usv.com/people/the-librarian/, https://www.usv.com/writing/2024/02/ai-aesthetics/
The X post generated live on the show: https://x.com/usv/status/1847354782941663523
Union Square Ventures is building an AI operating system to support their investment team.
But it’s not what you think: It’s a constellation of AI tools that captures and synthesizes the firm's collective wisdom. It’s evolving every day, and Matt Cynamon is the mad scientist in charge
Matt calls himself a “regular” at USV. In practice that means he’s responsible for running experiments with AI for the firm. As an inherently curious person with the professional obligation to tinker, he’s built a suite of tools for the firm, including:
I sat down with Matt to talk about how AI is enabling him to bring his ideas to life as a generalist, get demos of the tools listed above, and exchange notes on all the other projects he has in the works at USV. We edit actionable insights extracted by an AI from meetings at USV and prepare them to be posted on the firm’s X handle live on the show. We even try out an art project at USV’s office called The Dream Machine, which generates art from conversations. Here’s a link to the episode transcript.
This is a must-watch for anyone interested in riding the AI wave by learning how to ship useful products quickly.
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:
Timestamps:
Links to resources mentioned in the episode:
Yohei Nakajima leads a double life.
By day, he’s a general partner of a small venture firm, Untapped Capital.
By night, he’s one of the most prolific internet tinkerers in AI. (He also sometimes works on automating his job as a venture capitalist.)
He’s the creator of BabyAGI (@babyAGI_), the first open-source autonomous agent that went viral in March 2023. Yohei has since released seven iterations of BabyAGI, a coding agent called Ditto, a framework for building autonomous agents, and, most recently, BabyAGI 2o, a self-building autonomous agent.
I sat down with Yohei to talk about:
We experiment with Ditto live on the show, using the tool to build a game of Snake and a handy scheduling app. Yohei also screenshares a demo of BabyAGI 2o in action.
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:
Timestamps:
Links to resources mentioned in the episode:
Yohei Nakajima leads a double life.
By day, he’s a general partner of a small venture firm, Untapped Capital.
By night, he’s one of the most prolific internet tinkerers in AI. (He also sometimes works on automating his job as a venture capitalist.)
He’s the creator of BabyAGI (@babyAGI_), the first open-source autonomous agent that went viral in March 2023. Yohei has since released seven iterations of BabyAGI (each one named after a different animal), a coding agent called Ditto, a framework for building autonomous agents, and, most recently, BabyAGI 2o, a self-building autonomous agent (that follows OpenAI’s unfortunate naming convention).
Even more incredible, Yohei isn’t a professional developer. His day job is as the general partner of Untapped Capital (@UntappedVC).
I sat down with Yohei to talk about:
We experiment with Ditto live on the show, using the tool to build a game of Snake and a handy scheduling app. Yohei also screenshares a demo of BabyAGI 2o in action.
This is a must-watch for anyone curious about autonomous agents, building cool AI tools on the internet, and the future of AI tooling.
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:
Timestamps:
Links to resources mentioned in the episode:
Yohei Nakajima: @yoheinakajima, http://yohei.me
Untapped Capital: @UntappedVC, https://www.untapped.vc/
My first interview with Yohei, around the time he released BabyAGI: https://every.to/chain-of-thought/this-vc-is-slowly-automating-their-job
The other AI tools Yohei has created: Ditto, BabyAGI 2, BabyAGI 2o
The tweet thread about AI bots being let loose on a Discord server: https://x.com/AISafetyMemes/status/1847312782049333701
This episode is sponsored by Reflect. It’s the ultra-fast note-taking app that’s about to change the way you take notes. To boost your productivity with advanced features like custom prompts and voice transcripts, give Reflect a try by clicking on this link: https://reflect.app/?utm_source=every&utm_medium=sponsorship&utm_campaign=september2024
Simon Eskildsen is a learning machine.
I first interviewed him in 2020 about how he leveled up from an intern at Shopify to the company’s director of production engineering by reading and applying insights from hundreds of books.
A lot has changed over the last four years. LLMs have made it possible to contextualize information like never before—and in this episode, I sat down with Simon to talk about how this changes the way he learns.
Simon is now the cofounder and CEO of AI startup turbopuffer, which is building a search engine that makes vector search easy and affordable to run at scale.
We get into:
How Simon’s learning rituals have evolved over time, as the cofounder of a growing startup and a new parent
The ways Simon has integrated ChatGPT, Claude, and Notion AI to do everything from writing legal documents to maintaining his rural cabin in Quebec
The custom AI commands in productivity tool Raycast that Simon uses to learn new words and cook creative dishes
Simon’s take on how language models will reshape the future of learning, especially skills like language acquisition, for the next generation
As we talk, we screenshare through his Anki setup, including the flashcard template he finds most useful, and try out his custom AI commands in Raycast to understand the meaning of two of my favorite obscure words, “lambent” and “eigengrau.”
This is a must-watch for note-taking aficionados and anyone who wants to supercharge their learning 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 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:
Introduction: 00:01:06
How entrepreneurship and parenthood changed Simon’s learning rituals: 00:02:51
How Simon accelerates his learning by using LLMs to find associations: 00:12:59
Simon’s Anki setup and the flashcard template he swears by: 00:18:24
The custom AI commands that Simon uses most often: 00:26:02
How Simon uses LLMs for DIY home projects: 00:37:45
Leveraging LLMs as intuitive translators: 00:40:48
Simon’s take on how AI is reshaping the future of learning: 00:51:38
How to use Notion AI to write: 00:59:10
The AI tools that Simon uses to write, read, and code: 01:08:53
Links to resources mentioned in the episode:
Simon Eskildsen is a learning machine.
I first interviewed him in 2020 about how he leveled up from being an intern at Shopify to becoming the company’s director of production engineering by reading and applying insights from hundreds of books.
A lot has changed over the last four years. Language models have made it possible to access and contextualize information faster, easier, and more cheaply than ever before—and in this episode, Simon and I talk about how this changes the way he learns.
Simon is now the cofounder and CEO of AI startup turbopuffer, which is building a search engine that makes vector search—an approach to information retrieval that uses machine learning to gather context—easy and affordable to run at scale.
We spent an hour talking about how he leverages LLMs’ contextual intelligence to supercharge his learning, such as helping him pick up new words as a non-native English speaker, do odd jobs to maintain his rural cabin in Quebec, and articulate technical concepts in legalese. As we talk, we screenshare through his Anki setup, including the flashcard template he finds most useful, and the custom AI commands he’s created in productivity software Raycast. Simon tells me about the clutch of AI tools he experiments with for journaling, writing, and coding, as well as his thoughts on how language models will fundamentally reshape the way we learn. Here’s a link to the transcript of this episode.
This is a must-watch for note-taking aficionados and anyone who wants to supercharge their learning 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.
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:
Simon Eskildsen: @Sirupsen
Simon’s startup, turbopuffer: turberpuffer.com, @turbopuffer
My first interview with Simon in 2020: https://every.to/superorganizers/how-to-build-a-learning-machine-299655
The productivity tool through which Simon uses LLMs, Raycast: https://www.raycast.com/
The other AI tools that Simon is experimenting with: voice-to-text tool superwhisper, copilot for developers Supermaven, code editor Cursor
How do two professional writers use AI to do the best work of their lives?
In today’s show, Every’s lead writer Evan Armstrong and I conduct an expert workshop on how we use ChatGPT, Claude, AI-powered word processor Lex, and the prompt builder that Every launched, Spiral, to feed our obsession with words—and help us write for more than 78,000 readers every day.
We talk about how AI helps us:
Understand our taste—understanding what good is
Pick a topic—knowing what to write about
Craft our words—everything from sketching out an outline to writing and editing
Build an audience—learn how to reach people
We get into:
How I used Claude and ChatGPT to help me identify the kind of writing I like—and why that’s critically important for mastery
How Evan uses ChatGPT to explore his taste across books, movies, and paintings
The way I use Claude Projects to help me turn a vast amount of research into a clear thesis statement for major projects
The routine Evan swears by to publish two pieces every week
How Evan and I use Lex to push through writer’s block and catch common writing mistakes like passive voice
My workflow inside Claude to craft emphatic metaphors
How we use Spiral to write viral tweets
Evan is the lead writer at Every who writes the column Napkin Math twice a week. He’s smart, funny, curious—and has the rare combination of business acumen, way with words, and crazy required to be a professional writer.
This is a must-watch for aspiring writers, or anyone whose job involves writing more than six sentences in a row.
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:
Introduction: 00:01:04
How to develop good taste: 00:04:28
Dan uses Claude to articulate his taste in books: 00:13:34
How to use LLMs to explore art cross different mediums: 00:21:06
The way Evan chooses his next essay topic: 00:33:45
Go from research notes to clear thesis in Claude Projects: 00:38:20
How Evan uses AI to master new topics quickly: 00:46:51
Evan leverages AI to power through writer’s block: 00:59:21
How to use Claude to find good metaphors: 01:04:28
The role of AI in building an audience: 01:11:44
Links to resources mentioned in the episode:
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
Links to resources mentioned in the episode:
Evan Armstrong: @itsurboyevan
The column Evan writes at Every: Napkin Math
Evan’s upcoming course about how to write with AI: https://www.writewithai.xyz/
The piece Dan wrote about using LLMs to articulate his taste: "What I Do When I Can’t Sleep"
Dan’s article about admitting that he wants to be a writer: "Admitting What Is Obvious"
The Browser Company isn’t just building a browser, they’re building a formidable brand—and they’re doing it with AI.
The Browser Company has driven viral user growth, a $550 million valuation, and close to 100,000 YouTube subscribers. Its brand centers people, not products. It’s messy, authentic, and refreshing—and it seeps into everything the team does, from the job descriptions on their website to announcing new features through short films and giving keynote addresses in diners.
I sat down with Nashilu Mouen-Makoua, the head of storytelling and a strategic advisor to the CEO at The Browser Company, to talk about how she’s weaving relatable stories around new technology.
We get into her philosophy around storytelling, including why she believes centering people is the key to building a memorable brand, The Browser Company’s focus on making technology accessible to a wide audience, and the brass tacks of how Nash’s team structures meetings to generate great ideas. Nash also tells me how she’s integrated LLMs into her workflow, to do deep research, get a gut check on a new article she’s written, and put the finishing touches on her words.
As Nash explains that the best way to position a product is in response to contemporary social context, we screenshare through her conversations with ChatGPT about the socio-political climate in America preceding the release of a Tracy Chapman song. We also use the LLM to simulate a group of Arc users and interview one of these imaginary personas live on the show to gather preliminary customer insights.
This is a must-watch for people who want to use AI to tell compelling stories about what they’re building in tech.
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
Links to resources mentioned in the episode:
Nashilu Mouen-Makoua: https://twitter.com/lafillemouen
The Browser Company: https://thebrowser.company/, https://twitter.com/browsercompany
Arc, the browser that reimagines the way we use the internet: https://arc.net/, https://twitter.com/arcinternet
Tracy Chapman’s song, Talkin’ About a Revolution: https://www.youtube.com/watch?v=Xv8FBjo1Y8I
Our TOPPODCAST Picks 
