This week, I was talking to my engineering friend, and he mentioned that he’d figured out a way to improve the output of his AI responses. He showed me how changing the prompt had resulted in a significantly improved response on something he was working on. But his insight was about how he improved the prompt. He asked AI to write the prompt for him! It returned a better prompt, which resulted in a better response. It was akin to him saying, Show me how to ask you questions in a way you understand best. Later in the week, I tuned in to a webinar in which the presenter used a similar technique to generate his prompts. I was hearing the same technique from two credible people in the same week.

I’ve been trying to improve my prompts for a few months, but I never considered this approach. I tried it today while I was using AI to help me with some tasks, and the results were much better. I’ve read and listened to a lot of stuff about prompting over the last few months, but this is probably the one thing that’s improved my prompting the most.

Going forward, I’ll ask AI to write or edit my prompts for me.

One thing that resonated with me in Warren Buffett: Inside the Ultimate Money Mind was the idea of studying failure. The book mentions that Charlie Munger studied failure to improve his decision-making. Munger studied the failures of others as a way of understanding thinking errors, which is studying psychology.

This got me thinking. I want to be more intentional about studying failure. I get excited about hearing what worked from entrepreneurs, but I need to be equally (or more) excited to learn about their failures and the why behind them. I’m really curious about psychology and want to keep improving my own decision-making, so this approach is appealing.

I think the first step is to regularly analyze my own failures and mistakes. I’m going to put some thought into ways I can make this a habit and see if I can adopt strategies others have used successfully.

I’m reading Warren Buffett: Inside the Ultimate Money Mind, which is a book about the mindset of Warren Buffett and other investors. One of the things it discusses is how Buffett and other investors make decisions. Robert Hagstrom points out that to understand psychology is to understand human decision-making. That’s why successful investors like Charlie Munger studied psychology to improve their own decision-making.

I’ve never thought much about psychology,  but this book got me thinking about it in relation to entrepreneurship—specifically, entrepreneurial wisdom. In this post, I shared that wisdom is the ability to apply knowledge in a manner that aligns with the outcome you desire. Wisdom means changed behavior and improved decision-making—knowing what to do and when to do it.

I’m always looking for ways to improve my decision-making (and share what I learn). But I’ve never really thought about trying to understand psychology to accomplish this until now. Hagstrom has me interested in learning more about psychology.

I’m going to try to find one of two books about psychology and add them to my reading list.

As I was poking around on the internet over the holiday, a book written by an indie hacker entrepreneur caught my eye. Traditional places like Amazon don’t sell the book. Instead, this entrepreneur is not only self-publishing but also self-distributing the book—the only place you can buy it is his website. I’ve seen this before, but it definitely piqued my interest.  

The founder does two things that made me lean in more (and want to purchase his book). First, he posts stats about book sales: total books sold since launch, total revenue generated, and number of books sold today were prominent. I hadn’t seen this before, and I loved it. I took it as his way of communicating how much value has been provided to others—in the aggregate and recently. And it’s more social proof.

Second, the book is never finished. He’s constantly updating it as he learns new things. He shows the last time he updated the content and the last time he published new book files. The book was written about five years ago, his last update was within the last twenty-four hours, and new files were published today (as of this writing). I like this approach because his book content stays current. I’ve never seen this before.

This entrepreneur is doing a great job of marketing his book, and he got me excited about it. I’m going to grab a copy and add it to my booklist.

I did a lot of reading this weekend for my “book library” MVP. I dug deep into retrieval augmented generation (RAG) and learned some helpful things:

• There are different variations of RAG: GraphRAG, StructRAG, LightRAG, etc. New versions have been introduced every few months this year. Which is the right one depends on your use case.
• Normal RAG isn’t great for a large data set like a book. It struggles to make connections when presented with a lot of data.  
• RAG’s results are better when you feed it relationships in a data set via a schema. GraphRAG, StructRAG, and LightRAG try to make up for this by using a knowledge graph to index the information better, which leads to understanding the data better and providing better results.

I’m realizing that how the information gets indexed in large data sets is critical, especially if I want to query across lots of dense data sets like books. Thinking about why entrepreneurs with photographic memories have an edge, I decided that their minds have done a superior job of indexing everything they’ve consumed and making nonobvious connections across the data. Those connections lead to unique insights that lead to creative solutions to problems or actions to get closer to their goal.

This weekend highlighted that I need to focus on and understand how information gets indexed as I evaluate RAG and other alternatives.

Today I read an article about a hack that helps you learn better. It suggests writing a one-page summary after you’ve read ten pages of a book because this increases your retention by 50%. The idea is that to learn, you must stretch yourself. You’re forced to do that if you have to process and organize what you consumed and then express your understanding in writing.

A few months back, I was writing a series of five or so blog posts for every biography or autobiography I read. I created a digest of each book and then shared the important parts via the blog series. Then, I began using the blog series to create a podcast series.

I was doing multiple levels of distillation, which helped me uncover insights from each book and retain more about each founder’s journey that I’d read about. Doing all of this weekly wasn’t sustainable, and I want to find a more sustainable process for doing the same thing. That’s why I’ve created an MVP to help me create book digests.

I’m a fan of writing. It’s a powerful practice that helps me organize my thoughts. When I write about what I’ve read, it feels like a superpower. I identify core concepts and insights I wouldn’t have found by reading passively, I retain them, and I can share them with others.

Writing about what you’ve read is something everyone can do, but most won’t. It’s more work, but I think the reward is worth the effort.

I’m using Google AI Studio to run one of the MVPs for my book project. Google’s AI is called Gemini, and there are eight different Gemini large-language models (LLMs). Determining which would yield the best result was a concern. Google had thought it through, though: AI Studio has a compare feature: you can ask a question and select two LLMs, and Gemini will provide responses from both of them in a side-by-side view.

I’ve been testing prompting and system instructions this week, and the compare feature has been helpful. Seeing how the different LLMs respond to the same question is helping me narrow my choices faster.

Google AI Studio has limitations, but it’s a good tool for someone who is nontechnical and wants to fine-tune their AI experience.

I’ve spent the last few weeks diving into Google’s AI Studio, NotebookLM, Vertex AI Agent Builder, and various other AI-related tools from Google and other companies. A developer friend has helped me a lot. I was aware of some of these technologies from reading about AI and LLMs in general, but now that I’m trying to use them to create solutions for my personal project, my understanding of them has gone much deeper.

I have a clear idea of what I want the technology to do. I’m trying to figure out if it can specifically do what I want. If so, what are all the ways? What are the implications of each option? What I learn sticks in my memory. This is different from my normal approach of poking around to understand a tool’s general capabilities, which doesn’t result in good retention.

I’ve also noticed that when I seek help from technically oriented people to learn new technologies, describing the problem and how I want to solve it helps tremendously. It gives them a better idea of where to start, and the conversation is more focused on solutions to my problem than on a broad overview of the technology.

I’m not sure which, if any, of these technologies will be part of the solutions I build. But I’ve learned something: If I have a problem I’m excited to solve, I should try using new technologies to create a solution. Worst case, I’ll gain a better understanding of the technologies. Best case, I understand the technologies better and create a solution to my problem.  

This year, I’ve read roughly twenty biographies and autobiographies about entrepreneurs in media—broadcasting, publishing, and cable. I didn’t plan to read so many books about this industry; it just happened as I followed my curiosity. As I read about one entrepreneur, I learned about competitors or business partners I wasn’t familiar with, so I found books on them too. Almost every book led me to at least one other person I wanted to learn more about.

Before I read all these books, I had zero understanding of media. I didn’t know its history, how people made money, or how it has impacted other industries and society. Now, I’m far from a media expert, but I have a working, high-level understanding of the industry and the strategies used to build large media companies. Reading books about numerous entrepreneurs back to back (mostly) helped me see the industry from different perspectives by way of each entrepreneur’s journey. This gave me a clearer picture of the industry and an understanding I wouldn’t have if I’d read about only one or two media entrepreneurs.

I gained lots of value from this media deep dive, and I want to mimic it in the future, but more intentionally. Next time, I’ll do a few things differently. The main thing is to start with a desire to understand a specific industry—and a clear reason why. Ideally, I’d be highly motivated to understand the industry to help me solve a specific problem. The other thing is to research the major players who helped create the industry and try to find books about them. Entrepreneurs who help build an industry in the early days and achieved outsize success are likely to have done business with, employed, or be connected to other entrepreneurs in the space.

Reading the life stories of multiple entrepreneurs in an industry feels like a major hack. I can’t wait to find out what the benefits are when I’ve studied several industries this way.

I published a six-part podcast series on Ted Turner, the visionary entrepreneur who created CNN and other cable channels like Cartoon Network and TNT under Turner Broadcasting System. He also owned the NBA’s Atlanta Hawks and MLB’s Atlanta Braves, and had a fortune of $10 billion at its peak. I really enjoyed his autobiography and learned a lot from it. If you're interested in learning more about Ted and his remarkable journey, you can start listening to part one in this series on Apple Podcasts here or Spotify here. Ted's journey is covered in episodes 98 through 103.