🎧 He Wrote a Book in 30 Days

TL;DR: Today we’re releasing a new episode of our podcast How Do You Use ChatGPT? I go in depth with Seth Stephens-Davidowitz, a data scientist, economist, and author. We dive into how AI is fundamentally reshaping the way we approach creative projects. Watch on X or YouTube, or listen on Spotify or Apple Podcasts.

Was this newsletter forwarded to you? Sign up to get it in your inbox.

New York Times bestselling author Seth-Stephens Davidowitz wrote a book in 30 days—and he did it with ChatGPT.

Who Makes the NBA? is Seth’s third data science book. He challenged himself to write it in under a month after realizing how much faster he could work by teaming up with ChatGPT plugin Advanced Data Analysis. Along the way, Seth discovered something else: AI made the process of writing this book way more fun. He handed off all the boring parts of data analysis, like writing code to generate charts from datasets, to AI. This freed him to focus on the part that he loves—thinking up questions designed to uncover insights from a dataset.

Seth is a data scientist, economist, and author of Everybody Lies and Don’t Trust Your Gut. He’s worked at Google, lectured at Wharton, and consulted for Fortune 500 companies.

Who Makes the NBA? is a fascinating read, but it’s also an experiment in how AI is revolutionizing creative pursuits. In a world where AI is making every question that humans know the answer to immediately answerable, the real differentiator is asking the right questions—a skill that Seth isn’t just exceptionally good at, but also finds joy in.

I sat down with Seth to understand where AI sits in his data analysis process and how he used it to write a book in 30 days. We also prompt ChatGPT to answer an intriguing question of our own—which Olympic sport I’d be best at—live on the show.

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). Here’s a taste:

Brainstorm acronyms with ChatGPT. Seth created a metric to rank basketball players after adjusting for their height and named it after Muggsy Bogues, the shortest NBA player in history. Since he wanted the name to double-up as an acronym that described the metric, Seth used ChatGPT to generate one that was “unbelievably, mind-blowingly good.”
ChatGPT as the ultimate productivity hack. Beyond creative brainstorming, ChatGPT’s Advanced Data Analysis feature saves Seth significant time by generating charts based on simple instructions. “[J]ust the fact that you could just tell it: Download this data set, run this regression, make a chart of that, and it does that right away, was so wild,” he says.
Clarify your thought process with ChatGPT. Seth uses ChatGPT to adjust specific variables, like colors and positioning of labels, in the charts that it has generated. He usually makes these micro-decisions while talking to ChatGPT, and explains that it’s “really nice to constantly be asking these questions and have the chart come back pretty much instantaneously.”
Focus on what you enjoy and outsource the rest to AI. With the time that ChatGPT saves him, Seth can concentrate on the work that he enjoys most: framing questions to unearth insights from a dataset. ChatGPT allows him to do this by handling “everything that [is] annoying” like scrubbing datasets and looking up code on how to make the charts.
Redefining who can be an artist. Seth also enjoys conceptualizing illustrations for his book—like “a piece of DNA dribbling a basketball between its legs”—and with AI tools, he can bring these ideas to life. Despite having “zero artistic talent,” Seth marvels that he’s “able to express this creativity that otherwise would be dormant.”
ChatGPT as a collaborator, not an oracle. For all these use cases, Seth emphasizes that getting the most out of ChatGPT is an iterative process of trial and error. “You can't expect [ChatGPT] to nail it on the first attempt…you have to start the conversation and build to the right answer,” he explains.
Learn how to identify ChatGPT’s flaws. Seth has developed an “intuition” about the areas in which ChatGPT is likely to go wrong in his line of work. He says that ChatGPT’s mistakes “tend to be really glaring and obvious,” making it easier to spot them.

In the next segment of the interview, Seth uploads a dataset of Olympic athletes—recording variables like height, weight, and type of sport—to ChatGPT, and we ask it questions to discover the Olympic sport I’m most suited for.

We input my height and weight to ChatGPT, and ask the model which sport I would have the most success in. ChatGPT attempts to identify which sport has the most athletes with physical attributes that resemble mine by filtering the dataset for athletes that are within a “tolerance range” of five centimeters (1.96 inches) of my height or five kilograms (11 pounds) of my weight.

ChatGPT to standardize data. Since the unit we use to input my height and weight is different from the one in the dataset, ChatGPT automatically standardizes the data. “Another one of those things that's just really nice that it just does that and you don't have to think about it,” Seth remarks.
Factcheck ChatGPT. ChatGPT generates a list of sports that have the most athletes that resemble my physical attributes, but Seth identifies that the result is skewed toward sports with more athletes overall. He explains, “It's going to be way over-weighted to people who have more sports, right?”
Use ChatGPT to make smart guesses. We grill ChatGPT with a few more questions based on the dataset, including limiting the study to American athletes and reducing the tolerance range. Even though ChatGPT may not generate the most precise response right off the bat, we agree that it’s an excellent tool for getting a quick ballpark estimate or “eyeballing” questions like this.

You can check out the episode on X, Spotify, Apple Podcasts, or YouTube. Links and timestamps are below:

Watch on X
Watch on YouTube
Listen on Spotify (make sure to follow to help us rank!)
Listen on Apple Podcasts

Timestamps:

Introduction: 00:47
How ChatGPT is making data analysis fun: 11:29
AI is redefining who can be an artist: 16:15
Brainstorm creative ideas with ChatGPT: 20:35
How Seth uses ChatGPT to instantly generate charts: 28:27
Develop a sixth sense about when ChatGPT is wrong: 43:20
Figuring out which Olympic sport I’m statistically best suited for: 50:20
ChatGPT takes an approach that surprises Seth: 52:15
We have an answer! The Olympic sport I should try out for: 1:02:25
The power of getting quick answers to previously unanswerable questions: 1:03:47

What do you use ChatGPT for? Have you found any interesting or surprising use cases? We want to hear from you—and we might even interview you. Reply here to talk to me!

Miss an episode? Catch up on my recent conversations with founder and newsletter operator Ben Tossell, a16z Podcast host Steph Smith, economist Tyler Cowen, writer and entrepreneur David Perell, Notion engineer Linus Lee, and others, and learn how they use ChatGPT.

If you’re enjoying my work, here are a few things I recommend:

Subscribe to Every
Follow me on X
Subscribe to Every’s YouTube channel
Check out our new course, Maximize Your Mind With ChatGPT

The transcript of this episode is for paying subscribers.

Thanks to Rhea Purohit for editorial support.

Dan Shipper is the cofounder and CEO of Every, where he writes the Chain of Thought column and hosts the podcast How Do You Use ChatGPT? You can follow him on X at @danshipper and on LinkedIn, and Every on X at @every and on LinkedIn.