A few days ago, a friend told me about Reducto. The company just raised over $24 million from venture capital firms to solve the problem of unstructured data in PDFs by making it usable. It structures the text in PDF documents so you can feed it into other systems, such as LLMs or your own applications.

Some companies are building solutions that require information from PDFs to be fed into their software to achieve a desired output. They spend a significant amount of time figuring out how to extract unstructured information from PDFs, which isn’t as easy as it sounds. The issue is that this isn’t what these companies specialize in, so it takes them a long time to figure out. In many cases, they build something that’s decent but not great. Reducto’s PDF-processing service lets them skip mastering PDF extraction. They use the output from Reducto and focus on the more important aspects of the solution they’re building.

I spent some time playing with the tool’s free version. A few notes:

• Reducto can scan any document and turn the entire document into structured JSON. The free version has a 30-page document limit.
• The tool is incredibly good at extracting information from charts, which isn’t easy.
• There are many useful settings, including extraction method, chunking method, and more.
• The tool has an API, which is great for automation.
• If you need the extracted data formatted in a particular way, you can create a schema in Reducto, and the output will be formatted using your schema. I love this feature.

This is an impressive tool that solves a boring but big problem for companies. I can see companies quickly agreeing to pay for this service, which likely led to rapid growth in revenue and caught the attention of venture capital investors.

I get the impression this service is built for enterprise clients. I wonder if Reducto plans to offer something that’s more suited to small or midsize companies.

I’m committed to reading a book a week to learn and improve. Usually it’s a biography or autobiography because I get the most from reading about entrepreneurs’ journeys. I’m also committed to sharing what I’m reading in the library section of this site. Each week, after I read a book, I share it in my Learning Library, as it’s called now. My goal is to post a new book every Sunday.

This week, I shared a biography I read about Charlie Munger. Several books have been written about the life of his business partner, Warren Buffet, but I wanted to learn about Charlie’s journey, too—specifically, how he came by his multidisciplinary way of thinking and solving problems.

Damn Right! was just what I was looking for. Not only did it offer great insights into Charlie’s early career and tragedy, it also included great context about his businesses before Berkshire (including his hedge fund), his personal life, his quirky personality, and his commitment to multidisciplinary learning.

If you’re interested in learning more about Charlie Munger, consider reading Damn Right! by Janet Lowe.

This week, I connected on X (formerly Twitter) with an investor who’s an avid reader. He does a great job of sharing what he’s reading and what he’s learning from the books he reads. From what I can tell, he’s a fan of biographies and investing books, as I am.

When I interact with avid readers who also share their learnings publicly, I get excited and curious to learn about their process. I’ve struggled with managing and later finding highlights in books I’ve read (see here). I’m trying to solve this problem for myself or at least reduce the pain. I asked this investor and learned that he’s doing a lot of what I’m doing: manual highlighting and making notes in physical books.

One thing he does stuck with me: He extracts quotes from books and stores them in a file, sorted by quote type. Retrieving a quote when he needs it is significantly faster than if he had to find it in one of many physical books.

Even though I send friends quotes from books all the time (by sending pics of the page with the quote highlighted), I don’t keep all the useful quotes I’ve read in a single place.

I’m glad this investor took the time to share his process with me. His approach to storing quotes is something I’ll replicate going forward.

I’ve been happy with this site’s new library section, which lists the books I’ve read in the last year (see here). I’m constantly referencing it and have gotten positive feedback on it. It was intended to help readers, but I constantly use it to find posts I’ve written that are connected to specific books.

This weekend, I looked at a stack of books I’ve read and realized that a material number of them aren’t listed on this site because I read them before 2024. I also realized that I don’t have a central place that captures all the books I’ve read over the last five or ten years, and that’s something I very much want.

So, this weekend I decided that I’m going to add all the books I’ve read to this site. It’s a long-term project, but it’s something I want to and will do.

This week, I caught up with a friend at a VC firm. We talked about books we’ve read recently and our reading habits, and I was excited by what he shared.

My friend unexpectedly read two books by different authors about similar topics. Normally, he’d read a book and then move on to the next one. But he’s started using ChatGPT to enhance his understanding of what he’s reading. He typed in his comprehension of and thoughts on points made in a book (he disagreed with the author) and asked ChatGPT for feedback. ChatGPT gave him feedback and pointed to another author who disagreed with the first author and could provide an alternative perspective on the topic. He read the book ChatGPT suggested and sought feedback as he read that book, too.

The result was that he read two books related to a topic he’s interested in. He was able to understand differing perspectives on the topic and debate his own perspective. All of this led to a deep understanding of the topic that he wouldn’t have gotten from the way he used to read as well as to deep conviction about his perspective on the topic.

This conversation reminded me of an Andrej Karpathy video that I wrote about a few weeks ago (see here). Karpathy also uses AI to help him read books.

I love to hear about anything that enhances people’s reading experience. I’m wondering if more people are starting to use AI to help them understand and retain what they’re reading. If so, how big could this trend get?

Today, I caught up with a friend who’s a serial entrepreneur. He’s an avid reader, so I told him about my book project and asked him a few questions about his reading habits. One insight is something I’ve heard from other entrepreneurs who like to read.

He reads physical books and reads on a Kindle, but he prefers the former. However, when he reads a physical book, it’s too time-consuming to retype sections he’s highlighted into his note-taking app. He reads on a Kindle because he can highlight with his finger and sync to his note-taking app. The problem is that he doesn’t like reading on a Kindle—but it’s the lesser of two pains.

I’ve not only heard this from several entrepreneurs, I’ve lived it. Getting notes out of physical books so they can be reviewed later is painful for me (see here). I endure the pain and read physical books, but I’m determined to solve this problem. If I do—and do it well—I think other entrepreneurs who are avid readers will embrace the solution!

I’ve been making daily learning a top priority for the last few years. Some time ago, I shared how I approach daily learning (see here). That list is still relevant, but the prioritization of the items has changed. I aim to read a biography a week, so that’s the method I focus on most. But I do a lot of other learning throughout the week. For example, I challenged myself to learn the big concepts around marketing (see why here) and have consumed a ton of information. I now have a better understanding of the big marketing concepts and how marketers think.

I’ve recently started creating notes documenting what I’ve learned, and from what sources. I’ve been sharing some of that with founders and friends. They’ve found it helpful. In blog posts, I share what I’m learning from books—but not non-book learning. I want to find a good way to share on my blog the best non-book information I’ve consumed.

I haven’t settled on how to do this, but an idea I’m thinking about now is a weekly list of the top five to ten sources I consumed that week and what I learned from them. I don’t want to keep good information to myself. I want to get into the habit of sharing more useful sources from which others can learn. I just need to figure out how to do it in a way that’s not a huge lift so I can do it consistently. I’m open to ideas. If you have suggestions, send them my way.

I began reading a new book that I’d put off reading for a long time: Poor Charlie’s Almanack: The Essential Wit and Wisdom of Charles T. Munger. I bought the 2005 version years ago. It’s a huge book with tons of pictures, so it’s awkward to hold and difficult to read. Stripe Press printed a version without all the pictures in late 2023 that’s the size of a normal book, making it more manageable. I bought the updated version and dug into reading it.

I’m still reading the book, but so far, I like it. A few high-level thoughts:

• Psychology – Robert Hagstrom’s books got me more interested in understanding psychology to understand human decision-making (see this post). Munger writes extensively about psychology and judgment. He reiterates the importance of understanding psychology if you want to do well in life. He shares mental models and stories that make understanding some of the big ideas in psychology easier. His insights on psychology and his views of its importance got me excited to learn more about the topic.
• Education – Munger is critical of higher education institutions, even though he graduated from Harvard Law. He highlights the gaps in how these institutions teach—or don’t teach—certain topics like psychology that make them difficult to apply in everyday life. His big gripe is that they teach these topics in isolation and don’t educate students on how they work in conjunction with other disciplines. They also don’t teach all concepts in a discipline; they selectively choose which ones to cover. He advocates for a multidisciplinary approach to teaching because it better reflects the complexities of the real world. He also advocates for learning all the big ideas in a discipline. He gives the example of how his law classes, such as negotiations, would have been enhanced by psychology concepts. He advocates for people to educate themselves by reading about the big ideas in a discipline such as psychology. The education you can give yourself can be better than what you get at a college or university because it can be multidisciplinary and include all concepts in a discipline.
• Multidisciplinary learning – Munger is a big believer in the idea that understanding lots of different disciplines and how they work together better prepares you to navigate life and, in his case, make better investments. Having mental models from the various disciplines enhances your ability to read situations and make decisions superior to those of others.

I’m glad I got around to reading this book. I’ve made lots of highlights and notes already. I’m looking forward to finishing it.

If you’re interested in the book, you can learn more about it and download a free PDF copy at Stripe Press here.

This week, an entrepreneur friend gave me feedback on a blog and podcast series I did on a biography. He said the posts resonated with him because of the insights I shared. Connecting the dots between different people and periods was helpful and would be hard for him to do himself. And because the insights derive from the experiences of people who did what he’s attempting to do, but on a massive scale, they’re more valuable because the people’s outcomes make them more credible.

I appreciate my friend giving me his candid feedback. The books I read are available to everyone, so it surprises me when people value the connections I make between ideas in different books. Because I discovered those connections, I assume others have also done so, or could have. But I’m learning that’s not common. I suppose this is because of the effort required to find important ideas in the sea of unstructured text that is books. And because of the dispersed nature of books.

My takeaway is to lean more into sharing the connections between ideas in various books. It’s tremendously valuable to entrepreneurs.

I was chatting with a friend who’s an entrepreneur about AI workflows and learning tools. He told me about a new product from Google. Gemini Advanced just released its deep research feature, an AI research assistant. It uses Google’s Gemini large-language models to research complex topics on the internet and generate a comprehensive report of its findings. Google describes it as an “agentic system that uses Google’s expertise of finding relevant information on the web to direct Gemini’s browsing and research.” My friend told me a story about how he used it to help him learn about a topic. The tool provided him with a thirteen-page report that got him up to speed on the topic quickly.

What I like about this tool is that it gives you a step-by-step plan for how it plans to research the topic before it starts, and you can edit the plan if you need to. The tool then begins researching by searching for phrases, learns from those searches, and then searches for new phrases to learn more. It concludes by compiling everything it learned in a single document, which can be exported in a Google Doc. Google's blog post goes into more detail and includes a demo. The downside is that the tool costs $20 per month. But you can try it for free for 30 days, which is what I’m doing.

Researching things online can be a pain; it’s not something everyone is good at. I’m excited about this tool because it has the potential to help everyone efficiently find the information online that’s helpful to them.