Today, I bought a book on impulse.

I was listening to an interview of an entrepreneur I’m researching. When asked about things that shaped his career, he mentioned a book and how it shaped his thinking—and I immediately bought it. I didn’t look at reviews. I didn’t look at the price. My purchase decision was already made.

I reflected on the purchase later. It wasn’t a biography or framework book. It was a historical book containing the author’s opinion about how past events contributed to boom-and-bust cycles. I wouldn’t normally be excited to buy a book like this, but I was excited about this one. But why?

Simple. It was recommended by someone I deem credible. And that recommendation carried more weight than other factors.

I know that recommendations are how most people buy books. But I hadn’t thought much about it in the context of my book project. I’m thinking about it now, and I think a lot of value can be added to other entrepreneurs if you can show them in a simple way which books credible entrepreneurs found helpful (in addition to all the other cool stuff I want to show them). The information is out there; it’s just not organized in a way that’s easy to use.

Social proof is a proven psychological phenomenon, and deploying it could be a great way to enhance discovery of books by entrepreneurs who’d find them helpful.

I need to think about this more, but those are my preliminary ideas.

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 56
• Total blog posts published: 357

This week’s metrics:

• Books read: 1
• Blog posts published: 7

What I completed this week (link to last week’s commitments):

• Read An Honorable Titan, a biography of entrepreneur and publisher Adolph Ochs, who bought The New York Times
• Caught up (mostly) and rekindled conversations with prospective developers

What I’ll do next week:

• Read a biography, autobiography, or framework book
• Reach out to two more developers about this project
• Explore using Gumloop, Lindi, and Manus to see if they can help with this project
• Adjust layouts for a list of entrepreneurs on my blog
• Crystallize and write down idea for a biography-related website

Asks:

• If you can get me an invitation code to Manus, please let me know!
• If you know any full-stack developers interested in working on the software for my current project, please introduce us!

Week two hundred sixty-one was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week related to this project. Just playing catch-up after being out for a few weeks.

What I learned:

• I’ve been seeing “vibe coding” references lately. A friend explained it to me as “using natural language to create actual code by prompting to focus on features and capabilities but not line-by-line code. It’s different from no code, which is building blocks. Vibe coding is what people are doing in cursor. They prompt something that writes an entire application for them.” This definition was useful to me.
• This same friend shared with me a free DeepLearning.AI course about vibe coding taught by Replit. I signed up for it. Enroll here.
• I had more conversations this week with developers, but when I was asked about the details of the technical stack, I could answer only some of the questions. My gut tells me this signaled negatively to one senior developer I chatted with this week. My developer friend is available and will help transition things, but I need to understand the stack better and be able to communicate how it all works together.
• I looked at data about the posts I’ve written about biographies. The long-form posts about part of an entrepreneur’s journey get more visits than the shorter posts about one takeaway. A few shorter posts have done well, but they’re the exception. I suspect that the longer posts are also shared more.
• I learned about Manus and Gumloop. Manus is an AI agent tool, and Gumloop is an AI workflow tool. They may be able to help me with certain aspects of this project. I plan to experiment with both.

Those are my struggles and learnings from the week.

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 55
• Total book digests created: 15
• Total blog posts published: 350
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 0
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read That Will Never Work, a biography about Netflix’s early years
• Helped one of my parents resolve their medical situation

What I’ll do next week:

• Read a biography, autobiography, or framework book
• Catch up on everything from the last two weeks

Asks:

• If you know any full-stack developers interested in working on the software for my current project, please introduce us!

Week two hundred sixty was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week related to this project

What I learned:

• This week, I continued helping one of my parents with a medical situation. I learned about neurological rehabilitation, but not much related to this project. 

Those are my struggles and learnings from the week.

I had a great conversation this week and gained some unexpected insights. I was catching up with someone I worked with years ago and haven’t talked to in a few years. He’s a talented software engineer, and I love getting his perspective because it’s so different from mine. Part of our conversation was about my latest project and his projects. He asked some good questions about my project, and I asked him a few about his perspective on my project. One of my questions was about his reading and learning habits.

He shared that he isn’t a big reader of books, but he sees the value in the wisdom recorded in books and he’s interested in the software I'm building. I asked more questions about how he’d use it. Here’s what I learned:

• He has no desire to start reading whole books; it’s too time-consuming.
• The ability to access a repository of solutions would reduce his need to create solutions from scratch. He could leverage what others before him figured out to create better solutions in less time.
• Using a tool like this could accelerate how he learns about specific things without needing to spend hours reading books. He would learn more without materially increasing the time he applies to learning.

This is an interesting use case because I didn’t anticipate nonreaders seeing value in what I’m building. But this conversation showed me that there are likely countless use cases I haven’t anticipated. When you present people with a way to save time, they quickly see the value in it. This software shouldn’t make people change their behavior but should complement what people are already doing (or not doing).

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 54
• Total book digests created: 15
• Total blog posts published: 343
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 0
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read Empire: The House That John H. Johnson Built, a biography about publishing entrepreneur John H. Johnson
• Got feedback from five people regarding alternative layouts for a list of entrepreneurs on my blog
• Selected one of those layouts

What I’ll do next week:

• Mainly, focus on helping my family resolve the medical situation
• Read a biography, autobiography, or framework book
• Make it possible for software to be hosted in the cloud instead of locally

Asks:

• If you know any full-stack developers interested in working on the software for my current project, please introduce us!

Week two hundred fifty-nine was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week

What I learned:

• This week, I helped one of my parents with a medical situation. I learned a ton about medicine, but not much related to this project.  

Those are my struggles and learnings from the week.

A friend sent me a video that Andrej Karpathy made about how he uses large language models (LLMs). According to his website, Karpathy was “a research scientist and founder member at OpenAI” before spending several years at Tesla as Senior Director of AI.

Karpathy shares lots of good info in his video, but it was one use case that prompted my friend to send it to me—and that stood out to me. Karpathy uses LLMs to help him read and understand books and research papers. Here are my takeaways:

• Nowadays, Karpathy mostly reads books using LLMs.
• Here’s his process:
  • Pull up the content (i.e., text) of the book.
  • Find the chapter he’s going to read.
  • The LLM likely knows what the book is about but won’t remember what specific chapters are about.
  • Remind the LLM about the chapter by pasting the chapter text into the LLM context window.
  • Ask the LLM for a summary of the chapter.
  • Read the summary.
  • Read the chapter.
  • If he has questions about what he’s reading, ask the LLM those questions.
• Reading a book with an LLM dramatically improves his understanding and retention of each chapter. It enhances his ability to understand material in fields he’s unfamiliar with or books written long ago.
• No tools exist that make it easy to do this, so he uses a “clunky and back-and-forth” process.
• He mentions that having the ability to highlight text and ask questions about the highlighted parts doesn’t exist but would be useful.
• Final thought: Don’t read books alone.

I’m glad my friend shared this video with me. It was useful to hear a detailed explanation of how someone leverages LLMs to understand book content. Although he has extensive experience with LLMs, his process is still cumbersome. The fact that he’s following this cumbersome process tells me that the value he’s getting from it must be immense.

The software I’m building will greatly enhance my understanding of the books I read with LLMs. Karpathy’s video confirmed I’m going in the right direction, that other readers are leveraging LLMs, and that they’re experiencing pain when doing so.

If you want to see this section of Karpathy’s video, it’s here. If you want to watch the entire video to see how he uses LLMs in life and work, see here.

On January 27, 2020, I had lunch with an entrepreneur friend. He encouraged me to share what I’d learned from scaling my bootstrapped company to over $10 million in annual revenue. I’m private and was reluctant, but I wanted to help others who were just like me when I started my company—people who didn’t know what they didn’t know. I agreed, and we began a 60-day challenge. We both posted content daily to help other entrepreneurs (see our challenge details here). That challenge began on March 9, 2020, and ended on May 10, 2020. I didn’t miss a day—and I learned to enjoy the habit of reflecting and writing every day.

That was five years ago. Since then, I’ve written and shared a post every single day. That’s over 1,825 consecutive days of sharing my thoughts. When I agreed to the challenge, I had no idea I’d still be posting five years later, but I’m glad I am.

Every March, I reflect on my writing journey. Here are a few reflections:

• Strike zone – I read a book a week, mostly biographies. I used to think of reading and writing as independent hobbies. But writing about the books I’m reading has enhanced my learning and thinking. Combining them feels like it’s put me in my strike zone.  
• Format – I’ve played with a few different formats for creating posts about biographies I’ve read. The format I like best is a deep-dive series about a biography (see examples here and here). I’m aiming to get back to that format, and I’m building software to help with the creation process.
• Luck – Bringing value to others by writing has increased my luck surface area and led to magnetic luck (more on luck types here). When I focused more on writing about biographies, it led to more magnetic luck. Entrepreneurs want to know what other entrepreneurs have figured out but don’t always want to read an entire book.
• Audio – Last year, I tested doing a solo podcast about the books I was reading. It was really an audio version of this blog. I did 100 episodes to get reps and learn. Audio is a powerful format but requires significantly more work than writing. Publishing a podcast episode daily wasn’t sustainable. I’ll revisit doing a podcast, but I’ll need more support next time, and I’ll test different formats.
• Level up – I want to take this blog to the next level and create more value for others. Adding a page detailing all the books I’ve read and creating a profile page for each book (see here) is an experiment and just the beginning.
• Annual contract – Every March, I’ve asked myself if I’m enjoying this and want to keep doing it. If yes, I re-up for another one-year contract with the option to renew. I’ve now signed through 2026.

Those are my reflections. I’m looking forward to the next year. I feel like year six will be epic!