Table of Contents
It’s recommended that us aging adults keep our brains active, so people read and play games like Sudoku. That is a step in the right direction. But I’ve been using AI as a learning coach on various topics and it it not just keeping my brain active. It is making it drink from a fire hose! I use Gemini for my AI stuff and it is amazing. I chose it because I bought a Chromebook a bit over a year ago, and it came with a free year of all of Google’s advanced AI (this marketing ploy was successful because I got hooked and recently paid for another year). I have friends who enjoy using other AIs like CoPilot, ChatGpt, Grok, and Claude and they love them so I won’t claim that what I show for Gemini could not also be done with the others. But my advice is to pick one, and stick to it. For my first couple of years of looking into AI I dabbled in several versions and did not get very deep or proficient. But I made a lot of progress in this last year sticking to just one.
Another caveat I need to make is that not all of the features I mention are in the free version of Gemini that anyone with a Google account can use. As far as I know most are, but I’m especially not sure about Deep Research.
I started out using Gemini for technical research, either in my own field or for medical related questions. I have a deep interest in any condition I or my friends are afflicted with! For this I love using Deep Research. You just start a Gemini session and pick “Deep Research” from tools. I goes out and finds a bunch of relevant websites and research papers to your query and then comes back with a detailed report. An important tip is to watch it for a minute or so. It will then tell you its plan and you have to hit start. I’ve made the mistake of going away for several hours, coming back and expecting my results, but it still is waiting for you to hit start. After you start it can take a while so it’s a good idea to leave that window and come back later. The first thing I’d point out is that you can get very good results more quickly in “fast” mode without using deep research. But for more detailed results and a nice report you can save as a document, I prefer “thinking” mode and deep research.
It also helps to explain what is your level of expertise, from an amateur hobbyist, which is me in various areas, or someone with professional expertise and experience. So for a technical issue related to math or engineering I will say “I have a PhD in mechanical engineering and experience in numerical methods, but only undergraduate level computer science and electronics background”. But recently I was asking something related to neuroscience, so I said “I have no professional background in neuroscience but am fairly well read in it as a hobby”.
I’ve previously written blog posts about some of my research results, such as modifying my training to accommodate my leaky heart valve. But recently I’ve branched into more “hobbyist” interests like neuroscience. I’ll give a specific result on that below. But first I want to give an overview of options. Your first choice is fast or thinking mode. Fast works great for most things, and gets quicker results (hence the name). Thinking is still pretty fast, but goes a little deeper. After setting one of these, which will remain the default for future chats, from the Gemini window, you can just make a query and get great results even if you are using it to learn a new topic. That is option 1. It will find a lot of information for you to answer your question, and sometimes make things like spreadsheets to explain concepts.
It will then suggest follow up queries “would you like me to investigate xxx” and you just have to say yes if interested. I’ve learned a lot chasing these. Option 2 is to put it specifically in learning mode by picking the “guided learning” tool, which I love. This will behave similar to a normal Gemini query but adds images and quizzes to help you learn. Here is how it describes itself: “A specialized interactive mode/tool within the app. Modular; it breaks topics into a structured “learning path.” Automatically integrates diagrams, videos, and images. Includes Canvas-based quizzes, flashcards, and study guides. Built on LearnLM, a model specifically trained on learning science.” The third option, which I mentioned above, is to turn on the deep research tool. But I don’t recommend that for a topic you’re trying to learn about, because it is a lot slower. Use deep research for stuff you’re already familiar with but to dive deeper in a specific area. Sometimes I’ll follow up a learning session with a deep research session then save the report from deep research.
A simple example: the health benefits of pickleball
I was afraid the neuroplasticity example I give below might scare people away because it still got technical even though I said I was an amateur in that field. Neuroscience is a pretty technical field, after all. So let’s start with a simple example where I told it to stay nontechnical. This is a query in Gemini with guided learning turned on: “Assume I’m an adult layman in this field, please keep the answer less technical. Is it true that pickleball has some health advantages for seniors”. The answer is still very informative including a quiz and suggestions for further study. Note I kept this chat short, but I can return to it chat later and keep learning. Results are here.
Another Example: The history of Neuroplasticity
This query started from a fun anecdote I’d read about. In the last 1990s the Dalai Lama asked visiting scientists an interesting question along these lines: Western science assume the consciousness and our minds emerge from our brains, which can be thought of as the mind is the software running on the brain, the hardware. Can anything the mind does change the brain? He was specifically thinking of whether meditation can change the brain. The existing paradigm in neuroscience was that our brains are only malleable in childhood, very little neuroplasticity exists in adulthood. So the neuroscientists all said the answer was no. But we now know they were wrong, spectacularly wrong, and neuroplasticity and how consciousness can affect it is now a hot topic in neuroscience. And some of the best evidence comes from imaging the brains of advanced meditators, including the Dalai Lama’s Tibetan colleagues.
So I queried “I have no professional background in neuroscience but am fairly well read in it as a hobby. I would like to know the history of developments in the understanding of neuroplasticity since the 1990s:. This led to a delightful interchange in which I learned quite a bit, which I’ve shared here.
I will be following up with weekly posts on areas relevant to healthy aging, both physical and mental, that I’ve investigated with Gemini. I will always make sure I give the AI credit. I don’t like it when people create blog posts or youtube videos with AI and don’t acknowledge it. I think that’s like cheating on your homework!
Share this:
Related
Published by
Published
