I aim to read one book a month. On my weekends, I sit on the couch with my coffee and my phone in another room. The purpose of this ritual is to create space in my schedule that is not limited by time and tasks – but as my reading list grows, I find myself trying to get through more pages and more books.
I wanted to see if I could use artificial intelligence to summarize the key concepts, lessons, and wisdom of a book that I knew I wouldn’t get to for months, or even years. Keep the beautiful prose for the physical page, but use AI to summarize non-fiction business books, for example.
I chose Deep Work by Cal Newport to test run on ChatGPT. After using various AI tools, I thought that ChatGPT, one of the most popular instant text chat tools, would do the job best. I also have the $20/month paid membership so I wanted to make the most of it.
But the mission wasn’t very successful – partly because of the plagiarism protections built into the tools (and rightfully so), and partly because it took a lot of rapid engineering and independent research to get something worth using.
Think about parameters
The first thing I learned was that ChatGPT does not have access to full manuscripts – to avoid plagiarism and respect intellectual property rights – and simply summarizes from existing information on the Internet.
If I’ve learned anything about AI, it’s that forethought is as important as the first request. I didn’t just want a big book review. I wanted to learn Newport’s big ideas, arguments, strategies, and frameworks about deep work so I could apply it to my own work.
So, I started the conversation with some setting of expectations.
- First, ask ChatGPT if it has access to the entire book.
- Tell ChatGPT I want in-depth knowledge, not a superficial overview.
- Get tips on how to apply key strategies to my freelance business.
- See if you can pull from reader reviews and comments for more surprising and actionable suggestions.
Requirement 1: “Do you have access to Cal Newport’s book, Deep Work?”
Not ideal, but I had an idea. I found a 6-hour audio clip on YouTube, so I asked if he could use it to summarize the book for me.
But there is no such luck. He told me to watch the video – another safeguard against plagiarism. Watch a video for six hours? This hardly saves time.
There are over 32,000 reviews of the book on Amazon, so I thought there might be enough reviews on the book to come up with an in-depth review. So I started from this angle.
Other request: “I haven’t read Cal Newport’s book, Deep Work. Highlight key ideas, concepts, strategies, and frameworks so I can apply it to my business as if I had. I don’t just want a book summary.”
ChatGPT had a hard time interpreting “comprehensive,” throwing out a ton of hints. He also started giving advice without asking me about my line of work, like “educate your team about the importance of deep work and provide training in time management and focus techniques” and “allocate dedicated blocks of time for deep work on the calendar ” He also gave general suggestions like “focusing on tasks that provide the most value and minimizing time spent on low-value activities.”
All pretty vanilla advice if you ask me. Time to apply the pressure, one question at a time.
I still wasn’t getting any breakthroughs, so I kept pushing.
OK, ChatGPT, I’m going to the Swiss Village.
I wish
I asked for an example of deep work in 2024 and we started to get somewhere. I liked the suggestion, about stacking shallow work.
As I do this instinctively, it was a helpful reminder to stack tasks and watch the context switch.
Google involvement to keep ChatGPT on track
At this point, I was using ChatGPT to ask random questions like if there is a limit on deep working hours.
He said a maximum of 4 hours of deep work per day.
I am reminded of a concept I like called the manager-maker schedule, which details the two main types of schedule. As a writer, I’m on a creative schedule, which means blocks of uninterrupted time are critical.
I had to do a quick Google search for the key lessons in the book so I knew what knowledge to push ChatGPT for. Apparently “productive meditation” was an important step, so I asked for more details about that.
Finally, a new concept. Deep work isn’t just upside down at desk time.
That strategy was unlocking – Googling for nuggets in the summary, then going back to ChatGPT to expand. When it did run, it was great.
I scanned a second review and found another concept that sounded interesting: keeping a compelling table. ChatGPT helped break down the concept.
TL;DR?
If you want to use ChatGPT to learn about a book, you’ll need to spend at least 30 minutes browsing reader reviews yourself and use the most interesting ideas to tailor your requirements. This inevitably takes up some of your deep work time. You can’t just ask the AI tool to do it for you.
Once you get down the road in this way, you may discover a concept that changes your productivity or your perspective—but ChatGPT still isn’t as good as just reading the book yourself.
You should also keep in mind that since ChatGPT doesn’t have access to the actual book and only the summaries and reviews that are available online, you might not even get accurate key points.
And whether using an AI overview defeats the purpose of a book on deep work is still up for debate.