Google recently offered NotebookLM users an exciting opportunity. Personal Notebooks can now be shared with others. The shared version is read-only, so the curator need not worry that unknown individuals could modify the existing work. Collaborative use of such a tool would represent a different opportunity.
I have written multiple posts focused on note-taking, collaborative note-taking, and the focus of AI on personal notes. These posts were related to, but a side focus of a career as an academic investigating study behavior and examining the application of cognitive theories of learning to taking notes. In a way, I have taken notes for years, focused on note-taking research. I have access to digital notes and highlights associated with hundreds of journal articles and books.
In a recent post, I described my approach to uploading a large body of these notes into NotebookLM, and now I can offer this content to any interested individual. I encourage you to take a look. What might be unique about my content is the amount of material and the personal process of generating this content through annotation and highlighting. My hope is that others will make similar offers.
When you use the link I provide (end of post), you will encounter the following interface. Ignore the references to Obsidian — this is the tool I use to accumulate digital content. This material was uploaded to NotebookLM. Try chatting with my content — green box in the middle, or use some of the suggestions made under the rightmost Studio column. I accumulated content mostly focused on study behavior, classroom applications of technology, and reading skills.
Here is a sample prompt you might try — How does the effectiveness of taking notes on paper compare with taking notes using a digital device?
Here is the link for access. It is not necessary, but if you have a reaction, I would appreciate a comment. Again, I think there is an opportunity for sharing here and hope offering my notes will provide an example.
My recent focus on losing an author’s perspective when consuming AI-generated content, particularly the AI response now preceding the typical hits generated by a search query, has encouraged a personal exploration of what might be a middle ground. I frequently use AI tools to chat with the notes and highlights I have generated in reading hundreds of journal articles and books. This body of content has a perspective of sorts because the notes I generate and the content I identify through highlighting reflect my personal way of viewing my field and represent ideas that both support and oppose scientific concepts and theories important to these topics. Any researcher who has relied on the accumulation of relevant articles over the years and makes use of PDFs rather than paper could do a similar thing to make extended use the content they have accumulated over the years. This accumulated body of content seems a great example of what the personal knowledge management advocates describe as a second brain.
Here, then, is what I believe to be an interesting question. Do AI chats with personally curated content provide different insights than a similar AI chat without this curated focus? Perhaps a more concrete example would be a better way to communicate my issue. So, I have the highlights and notes I have accumulated from years of reading in a designated area (e.g., educational applications of cognitive psychology), and I can chat with this content using identifiable services (e.g., NotebookLM). Would the reply to a prompt applied under these circumstances yield different insights than the same prompt applied using an AI tool not focused on a designated body of content (e.g., Perplexity)?
At first, this might seem a silly comparison. Certainly, one could find a biased assortment of resources taking a common flawed view on a topic, and then show that AI limited to consolidating this content would yield different prompt replies than similar prompts asked of an unfocused AI tool. But this does not seem to be what those building a second brain think they are doing. They would likely be offended by the suggestion that their efforts were for naught, and AI queries would yield more accurate information. They would probably suggest they are doing exactly the opposite. They are using their expertise to identify high-quality sources, and their notes would address both the strengths and weaknesses of the sources they curate. I am not certain the outcome of my proposed comparison is obvious.
My Test Case
I write a lot about study behavior and have found the controversy involving whether learners are better off reading and taking notes using paper or digital content of some interest. While many researchers suggest paper is superior, my personal experiences and focus on the benefits of previous learning experiences over time, see a unique value in digital processing. Simply put, highlights and annotations saved and organized offer advantages over a year or 50 years later that most would find difficult to replicate with paper. Even over short periods, studying is more than simple review, and digital tools offer unique opportunities for “post processing”.
The specifics here are important only if the type of information generated in pursuit of the information I encounter would change as a function of how I might use AI. I provide the background material because the topic could interact with the different uses of AI I identify in ways I cannot anticipate. Part of what I propose is that others with different collections of digital content might replicate the test I am applying to their own material and share their observations. There are so many uncontrolled variables I assume that while this is an interesting issue, personal preference will always be the deciding factor. Variations in topic, tool, and prompt could result in different conclusions.
The Prompt I used follows. The variation of the prompt I used when engaging a non-focused use of AI simply eliminated the phrase “Using my notes and highlights”.
Prompt: Using my notes and highlights, write a 400 word blog post comparing the advantages and disadvantages of reading and taking notes from paper and digital devices.
I used the directed prompt with Mem.AI, NotebookLM, and Smart Connections (Obsidian plugin). Perplexity was used as the nondirected AI tool. I will offer my observations first and provide the full prompt responses at the end as Appendices.
Sources – Perplexity is unique in comparison to other chat tools in that it provides specific sources for comments it generates. These tend to be what I would call secondary sources (see list following the Perplexity example). In contrast, see the sources in the Mem.AI responses. The names that appear are a crude version of the citation method academics use to reference journal articles and books (which were the sources I highlighted and annotated). One way to think about this may be that Perplexity is accessing the summaries generated by various individuals who have read primary sources, while Mem is accessing my personal summaries of similar sources. If identifying primary sources is important, it is easier to do this when you can show what these sources were.
Identification of unique insights – It would seem that an AI analysis based on specific notes, highlighting, and source selection would generate an output more useful for tasks you want to pursue. While obvious if the content of interest was selected with a task in mind and based on a small amount of material, this is not the way a “second brain” is built. The hundreds of sources I have collected represent a wide range of topics in my field. Specific topics of interest emerge within this process of more general learning, and part of the assumption in using a second brain is that the broader background will reveal connections that may not have been anticipated. The hope is that the application of AI, rather than basic searching, will help surface such connections.
With the exception of the sources cited, much of the information in the two types of searches was similar. Perhaps asking for a 400-word blog post as an outlet was not the best way to reveal subtle differences. I will direct your attention to sections I have highlighted in the NotebookLM and Perplexity prompt responses. Both NotebookLM and Perplexity provide citations that do not appear when copying the text. Because I was looking for comments related to the use of content over time, I was paying attention to any mention of searching or other mentions of delayed activity. The Perplexity response did not offer a citation. The NotebookLM output mentioned export, organization, and search. In addition, there were multiple citations, and the linked citations identified notes and highlights in the digital form.
Summary
AI tools with various capabilities are now available. For those of us who read digitally, we have the opportunity to export highlights and annotations that can be stored over time. AI can be used to chat with this stored content. My interest here was an attempt to determine if there was a unique value in applying AI to such content in comparison to asking questions of AI without this targeting of curated information.
I doubt the effort I describe here would convince anyone to change their existing strategy, but my hope is that I have offered an approach they might try to explore the options that are available.
************
Appendices
Mem.ai
The debate between reading and taking notes on paper versus digital devices is a nuanced one, with research highlighting various advantages and disadvantages for each medium. While digital tools offer convenience and speed, traditional paper methods often promote deeper cognitive engagement.
Advantages of Digital Reading and Notetaking
Digital devices offer several benefits. For instance, digital note-takers tend to record more content, including more verbatim lecture strings, due to faster typing speeds compared to handwriting Luo et al 2018. This increased volume of notes can be beneficial for later review, especially when notes are not immediately studied Luo et al 2018. Digital platforms also facilitate collaborative note-taking, allowing students to share the cognitive load and potentially create more complete notes Courtneyetal2022. Furthermore, digital tools can offer features like multimedia integration and online research capabilities, enriching the learning experience Yamac et al 2020. For example, digital writing instruction with tablets has been shown to improve writing performance and knowledge in primary school students, partly due to features like class blogs and multimedia components Yamac et al 2020.
Disadvantages of Digital Reading and Notetaking
Despite the advantages, digital reading and note-taking come with notable drawbacks. A significant concern is the potential for distraction. Studies suggest that the perceived advantage of longhand note-taking in some research may be attributed to the distractions inherent in digital devices, such as web surfing and social media Voyer 2022 summary. This can lead to shallower processing of information SingerAlexander2017b. Research indicates a “screen inferiority” effect, where reading comprehension can be lower on digital devices, particularly for informational texts and under time pressure Delgado2018. This effect has even been observed to increase over time Delgado et al 2018. The lack of physical cues, like the feel of pages, in digital reading can also hinder the formation of a mental map of the text, impacting comprehension of chronology and temporality Mangen et al 2019.
Advantages of Paper Reading and Notetaking
Paper-based methods often foster deeper engagement and better retention. Handwriting, being slower than typing, forces individuals to process and summarize information, leading to a more generative encoding of knowledge MuellerOppenheimer2014. This deeper processing can result in better performance on conceptual questions
MuellerOppenheimer2014. The physical act of writing and the tactile feedback from paper contribute to a stronger mental representation of the material Mangen et al 2019. For instance, studies have shown that paper readers are better at recalling “other relevant information” and performing better on questions related to key points SingerAlexander2017b.
Disadvantages of Paper Reading and Notetaking
While beneficial for deep processing, paper note-taking can be less efficient in terms of speed and volume compared to digital methods Luo et al 2018. It also lacks the inherent searchability and organizational capabilities of digital notes, which can make retrieval and restructuring of information more challenging SmartWisdom. Converting highlights from paper to more elaborate notes can also be a more cumbersome process Highlighting&fleeting.
In conclusion, the optimal choice between paper and digital depends on the specific learning goal and context. For tasks requiring deep comprehension and conceptual understanding, paper often holds an advantage. However, for efficiency, volume, and collaborative efforts, digital tools offer compelling benefits, provided distractions are managed effectively.
************
NotebookLM
Here’s a look at the advantages and disadvantages of reading and taking notes using paper versus digital devices, drawing from the sources provided:
The rise of digital devices has shifted how many people read and take notes. However, research comparing reading from paper and screens reveals a complex picture, with nuances depending on the text type, reader’s age, and even the specific device used. Several meta-analyses indicate a general advantage for reading comprehension when reading from paper compared to screens, particularly for informational texts. This paper advantage has even been found to increase over time. However, this difference is often not seen with narrative texts, and studies comparing reading on tablets specifically have sometimes found smaller or no significant differences compared to print.
When it comes to note-taking, there’s also ongoing debate about the best method. Some studies comparing handwriting and typing notes have found a benefit for handwriting notes, particularly for understanding concepts. This has been attributed to the slower speed of handwriting, which may encourage more summarization and paraphrasing rather than simply transcribing verbatim, leading to deeper cognitive processing. However, other research and meta-analyses have found inconsistent results or no significant overall difference between handwritten and typed notes. Some studies suggest that typing can lead to more complete notes, and note completeness can be related to better performance.
Digital tools offer powerful affordances for reading and note-taking, such as the ease of highlighting and adding annotations directly to the text. Digital notes and highlights can be easily exported, organized, and searched later. Digital environments also facilitate collaborative annotation and note-taking. However, digital environments can also present challenges. They may be more prone to distractions, and frequent use of digital media, particularly for quick interactions with short texts (like social media), may contribute to the development of shallow reading habits like scanning and skimming. Some online content may also have lower linguistic quality.
Ultimately, the effectiveness of reading and note-taking, whether on paper or digitally, depends significantly on the strategies and cognitive processes employed by the reader. While paper might offer some advantages for deep comprehension of informational texts and handwriting for conceptual processing, digital tools provide powerful functionalities for capturing, organizing, and retrieving information, as well as facilitating collaboration. Focusing on how one engages with the material and utilizes the tools, rather than just the tool itself, is likely key to effective learning.
The following is a screen capture of the original view of the highlighted section described above.
****************************
Prompt: Write a 400 word blog post comparing the advantages and disadvantages of reading and taking notes from paper and digital devices.
From: Perplexity
Comparing Reading and Note-Taking: Paper vs. Digital Devices
Choosing between paper and digital devices for reading and note-taking is a personal decision shaped by convenience, effectiveness, and lifestyle. Both formats offer distinct advantages and disadvantages.
Advantages of Paper
Better Comprehension and Retention: Studies show reading from paper leads to higher comprehension and test scores. Students who read print books outperform those who read digitally, and handwritten notes often result in better memory retention compared to typing[1][6].
Fewer Distractions: Paper books and notes keep things simple—no pop-ups, notifications, or temptations to multitask, which helps maintain focus[1][6].
Emotional Connection: Many readers find a deeper emotional bond with physical books, appreciating the tactile experience and the satisfaction of seeing their progress[1].
No Power Needed: Paper never runs out of battery and is always ready to use[1][6].
Disadvantages of Paper
Storage and Portability: Physical books and notes take up space, can be heavy, and are cumbersome to transport, especially when traveling or moving[5].
Accessibility: Finding a specific book or note can be time-consuming, and you must visit libraries or bookstores for new material[5].
Environmental Impact: Paper production contributes to deforestation and environmental harm[5].
Vulnerability: Paper can be easily lost, damaged by water or fire, and is harder to back up[5][6].
Advantages of Digital Devices
Convenience and Accessibility: Digital libraries offer instant access to thousands of titles and notes, all stored on a single device. Searching for information is quick and efficient[3][4].
Eco-Friendly: Digital reading and note-taking reduce paper usage and environmental impact[3][4].
Interactivity and Multimedia: eBooks and digital notes can include videos, images, and interactive elements, making learning more engaging[3][4].
Collaboration and Organization: Digital notes are easy to organize, search, and share. Real-time collaboration and version control are possible, which is ideal for group work[4].
Accessibility Features: Text-to-speech and adjustable font sizes make digital content more accessible to people with different needs[3].
Disadvantages of Digital Devices
Distractions: Devices can tempt users with games, notifications, and other apps, reducing focus[6].
Lower Retention: Typing notes can lead to lower retention compared to handwriting, as it often encourages verbatim transcription without deeper processing[6].
Dependence on Power: Devices need batteries and charging, which can be limiting in certain situations[6].
Cost: Digital devices are more expensive upfront than basic paper and pen[6].
Conclusion
Paper excels in comprehension, retention, and simplicity, while digital devices shine in convenience, organization, and collaboration. The best choice depends on your priorities—whether you value focus and memory or accessibility and efficiency. Many find a hybrid approach, using both formats as needed, offers the best of both worlds.
“Before the web did anything, Hypercard did everything” was the subtitle of an Ars Technica article I cited and liked in 2019. I use it here to celebrate the life of Apple software genius Bill Atkinson following his recent passing. HyperCard played a significant role in my academic career, and while I have written about the personal connections in the past, one more mention seems appropriate. Hypercard, often called a software erector set, was innovative and accurately foretold many future innovations we now take for granted.
Among the unique features were:
Hypertext/hypermedia
Object-oriented programming
Low bar / high ceiling software
I will attempt to call attention to these features as I offer a brief description. I spent hundreds of hours developing educational applications in Hypercard and would love to display some screen captures of my work. Unfortunately, Apple last updated HyperCard in 1998. I do have some old discs with my original work, but neither an appropriate drive nor an Apple operating system suited to run HyperCard. For a few images, I used my phone to capture from a textbook I wrote with my wife in 1996. One more comment. While I did work on HyperCard stacks for hundreds of hours, that was 25 or so years ago, so I may be fuzzy on some of the details.
The analogy – a stack of cards
Card, field, button
HyperCard was based on a hierarchy of objects. The most basic and encompassing element is a stack. A stack is made up of cards. Each card has a background and a foreground to which the user could add elements, such as text, images, text boxes, and buttons. The difference between the background and foreground was important when a card was duplicated. Typically, cards were intended to look the same with only key elements changing (e.g., a unique image, text information). Rather than create each card from scratch, it was possible to duplicate a card to retain the background and then add the unique features.
The following image shows a card from a series of cards built to provide information about the birds most commonly found in North Dakota. There are several text fields and buttons that would be common across all cards, and a unique image and descriptive text for each species. HyperCard, in this case, was used as a type of database.
Adding Action – Hypertalk was the language of HyperCard
Nearly anything done with HyperCard, e.g., opening a stack, clicking on a button, generated what was called an event. Events had no consequence unless there was a handler available appropriate to that event. A handler was pretty much a segment of code that would be executed when the relevant event was encountered. So, for example, mouseUp would respond to a mouse click.
On mouseUp
go next
End mouseUp
This handler added to a button would advance the card from a stack that was visible to the next card.
A unique feature of HyperCard, consistent with the philosophy of low bar, high ceiling, was that HyperCard would write many of the basic event handlers for you. You could do many things without coding, but also use the powerful scripting language, hypertalk, to do much more.
HyperCard came with a large assortment of symbols many appropriate as buttons (first image). However, when added to a card, the symbols were inert unless scripted. It was easy to find and add a button to a card, but then HyperCard was willing to help make the button do something (Button actions 1 and 2). The process here was to select an icon from button choices and then select the desired action.
Some of the button choices
Button Actions 1
Button Actions 2
If you opened the script for the button created in this fashion, you would see the script I included above as an example. Of course, once you learned hypertalk, the scripting language, you could just input this script from the keyboard.
Scripts could be added to most HyperCard objects and created actions originating from the object to which the script was attached. There was no single program, but rather a collection of programs associated with the various objects from which a stack was assembled (object-oriented programming). Events associated with one object (say a card) might trigger a handler somewhere else, where it would make more sense. I think of this as an event looking for a home. If an event does not find a handler on the object that generated the event, it falls through the HyperCard hierarchy to the next level. Because so many actions generate an event, every mouse click, opening of a card, opening the stack, etc., many do not find a handler and nothing happens. If you forget to assign a “go to the next card script” to a MouseUp associated with a button, nothing happens.
I have tried to find an old online manual that might provide a complete exposure to HyperTalk without luck. This description of hypertalk from Wikipedia includes sufficient samples of scripts to offer a way to consider just how powerful the language could be.
What I did with HyperCard
I used HyperCard for a variety of things. Here are a couple of examples.
The North Dakota Wild clipart collection
I used my tech skills outside of my role as a college professor. I had an interest in technology applications in science education and was interested in project-based learning. North Dakota Game and Fish had a program called OWLS (outdoor wildlife learning sites) and gave small grants to schools to support the development of small sections of land (think native plant gardens) associated with schools. I became involved in attempting to create activities and develop the sharing of project ideas between schools using technology. One of the projects involved the creation of HyperCard stacks of North Dakota Wildlife. The image used here was from the Bird stack. The idea was to provide students with images that the students could use in their own creations. The entire collection of images is still available from my server. Again, to imagine how this resource might be used, you have to put yourself back in time more than 20 years.
Technology Enhanced Study
Much of my academic research concerned study effectiveness, and I was particularly interested in large lecture, introductory, college courses. The freshman lecture course represents an interesting case. It places the least experienced students in a setting that is the most impersonal and most isolating of their college experience – heavy reading loads, long lectures, and the expectation that you process the inputs without guidance to take high-consequence exams that are likely unlike those you took in high school. My interest was in helping student identify their areas of weakness as they studied and providing an efficient way to address any weaknesses identified. You don’t need to review the entire chapter again. Study the poorly understood sections or ask a colleague for assistance with the topics you don’t understand. Don’t just mindlessly go over the same material again and again.
The course I had in mind was the Introduction to Psychology. I had access to the test item database provided by the textbook company (approximately 200 MC questions for each chapter). The items from the test bank included associated page numbers from the book and what I would call topics (maybe 20-25 for each chapter). Topics were simply identified by number and designated a group of questions addressing the same topic and section of the chapter. These questions provided the basis for the digital study environment I provided to students. Half of the questions for each chapter were used in the study tool, and the other half were reserved for possible use on examinations
The HyperCard study tool took me most of three months during a sabbatical to write. A study experience from the perspective of a student would work like this. Opening the stack on a Mac would offer the student the option of working on one of several chapters (usually 1-4) covered on the next examination. Once selected, Hypercard would display a randomly selected multiple-choice item from that chapter. The student would respond and the computer would then indicate whether the response was correct, and if not, the page numbers in the textbook associated with that question. The idea was that the student could use their textbook to review the page or so associated with that question and possibly take a note in their notebook or highlight the textbook. If the response was incorrect, the stack would then select another item at random from the other items with the same topic number. This would not guarantee a direct test of their understanding of a specific issue they found difficult, but at least would address the same topic. If correct, the system would select another topic at random from the chapter. As the student worked, the stack recorded the date and time of each response and whether the response was correct or incorrect. Aside from general performance, the data allowed consideration of when during the interval between examinations the student used the system (was the student cramming or studying systematically) and the time delay between questions. The delay following incorrect responses was regarded as particularly important because longer median delays were assumed to indicate targeted rereading, notetaking, or some other form of reflection. Students who showed little difference following correct and incorrect responses were using the system in a more passive manner, possibly assuming that responding to the questions alone was beneficial.
The process of preparing the HyperCard study tool was augmented by other Hypercard programs that would take a flat file of questions and create the full study tool by creating the study tool card by card adding a card for each line of text from the flat file representing one question. A procedure built into the Study Tool stack also exported data and added an identifier for the student who had used that specific stack.
Making this system work also required some concessions. Many students were not assumed to have their own Macintosh computer, and for research to be meaningful, access to the tool had to be standardized. At the beginning of each course segment, I took trays containing 200 disks to the reserve desk of the library. The library had a Mac lab always available to students. The disks were assigned an identification number with each student assigned their own disk that had a unique bar code so the disks were checked out in the same manner as other material made available for a specific course. After each exam, I would collect the disks, dump the data for analysis, and prepare the same disks with the questions appropriate to the next examination.
Readers who are familiar with such topics as comprehension monitoring, retrieval practice (testing effect), and distributed versus massed practice should be able to identify the theoretical bases for the tool and how I intended it to be used. What may not surprise educators is the finding that study opportunities are typically designed to address recognized study challenges, yet when released into the wild, students do not use them as intended. The tool was great for investigating actual student study behavior, but the benefits assumed are more difficult to generate than one might think. Capable students not really needing support flocked to the study tool. They used it more frequently and as intended. When answering questions incorrectly, their post-question delays were longer, indicating they were engaged in some effort to act on this awareness. This is not to say that students who were more likely to need help received no benefit, but the difference in who used the system and who used it most appropriately was one of the more challenging findings.
Eventually, I moved on from HyperCard to create online versions of a technology-enabled study environment using a small server, PHP, and MySQL. Students could work from their dorm rooms or any location with Internet access using their own equipment and any browser. My interest in actual student study behavior was more authentic when it did not require a trip to the library. Still, HyperCard was a way to get started and provided a sophisticated, user-friendly experience. For anyone who finds this type of research to be interesting, my published studies based on the study environments can be picked from the list of my publications provided by Google Scholar.
One final Bill Atkinson product
When Bill retired, he began working on one final vision. He lamented the total focus on online image collections and wondered what physical objects would remain to save personal memories. His passion project resulted in PhotoCard was a tool for creating personal postcards. These cards could be sent using the Internet, but Bill really wanted you to pay a small fee to have him print cards you created and he would send them for you.
I corresponded with Bill about PhotoCard and explained I had been a fan since HyperCard. I ended up with this mental image of him personally printing these postcards on his high-quality printer and making the effort to make small adjustments to get things just right. Then, he would head off with a box of these cards to mail them at the post office. This was not about the money as seemed his general approach. This was about making great things that people would use.
Bill Atkinson will always be one of my technology heroes.
Manage Consent
To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions.
Functional
Always active
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
Preferences
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
Statistics
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
Marketing
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
You must be logged in to post a comment.