We older adults are advised to keep our brains active so people read and play games like Sudoku. This is a step in the right direction. But I use AI as a learning coach in a variety of subjects, and it doesn’t just keep my brain active. He makes it drink from a fire hose! I use Gemini for my AI and it’s amazing. I chose it because I bought a Chromebook a little over a year ago and it came with a free year of all Google’s advanced AI (this marketing ploy was successful because I stuck around and recently paid for another year). I have friends who enjoy using other AIs like CoPilot, ChatGpt, Grok and Claude and love them, so I won’t claim that what I show for Gemini couldn’t be done with others. But my advice is to pick one and stick with it. In the first couple of years of researching AI, I dabbled in various publications and didn’t get very deep or proficient. But I’ve made a lot of progress in the last year, sticking to just one.
Another caveat I have to make is that not all 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 not particularly sure about Deep Research.
I started using Gemini for technical research, either in my field or for medical questions. I have a deep interest in whatever ailment I or my friends suffer from! This is why I like to use Deep Research. You simply start a Gemini session and select “Deep Research” from tools. I go out and find a bunch of relevant websites and research papers for your question and then come back with a detailed report. An important tip is to watch it for a minute or so. He will then tell you his plan and you must begin. I made the mistake of leaving for several hours, coming back and waiting for my results, but it’s still waiting for you to start. After you start, it may take a while, so it’s a good idea to leave this window and come back later. The first thing I would like to point out is that you can get very good results faster in “quick” mode without using deep research. But for more detailed results and a nice report that you can save as a document, I prefer the “think” mode and deep search.
It also helps to explain what your level of expertise is, from an amateur hobbyist, which is me in various fields, or someone with professional expertise and experience. So for a technical subject related to math or engineering I will say “I have a PhD in mechanical engineering and experience in numerical methods, but only an undergraduate level in computer science and electronics”. But recently I was asking something related to neuroscience, so I said “I don’t have a professional background in neuroscience, but I’m pretty well read in it as a hobby.”
I have previously written blog posts about some of the results of my research, such as modifying my training to accommodate my leaky heart valve. But recently I’ve branched out into more “hobby” interests like neuroscience. I will give a specific result for this below. But first I want to give an overview of the options. Your first choice is fast or think mode. Fast works great for most things and has faster results (hence the name). The thinking is still pretty quick, but it goes a little deeper. Once you set one of them, which will remain the default for future conversations, from the Gemini window, you can simply ask a question and get great results even if you’re using it to learn a new topic. This is option 1. He will find a lot of information to answer your question and sometimes create things like spreadsheets to explain concepts.
It will then suggest follow-up questions “would you like me to investigate xxx” and you just have to say yes if you’re interested. I’ve learned a lot chasing these. Option 2 is to specifically put it in learning mode by selecting the “guided learning” tool, which I like. This will behave similarly to a regular Gemini quiz, but adds images and quizzes to help you learn. Here’s how it’s described: “A specialized in-app interactive feature/tool. Modular, breaks topics into a structured ‘learning path’. Automatically embeds diagrams, videos and images. Includes canvas-based quizzes, flashcards and study guides. Built on LearnLM, a model specifically trained in science learning.” The third option, which I mentioned above, is to enable the deep research tool. But I don’t recommend it for a subject you’re trying to learn, because it’s much slower. Use deep research for things you’re already familiar with, but to dive deeper into a specific area. Sometimes I will follow up a learning session with a deep research session and then save the report from the deep research.
A simple example: the health benefits of pickleball
I was afraid that the example of neuroplasticity I give below might scare people because it still got technical, even though I said I was an amateur in this field. After all, neuroscience is a fairly technical field. So let’s start with a simple example where I said to keep it non-technical. Here’s a question in Gemini with guided learning enabled: “Let’s say I’m an adult layman in this area, keep the answer less technical. It’s true that pickleball has some health benefits for the elderly.” The response is still very informative, including a quiz and suggestions for further study. Note I kept this conversation short, but I can come back to this conversation later and continue to learn. The results are here.
Another example: The history of neuroplasticity
This question started from a fun anecdote I had read about. In the last decade of the 1990s the Dalai Lama asked visiting scientists an interesting question in this direction: Western science assumes that our consciousness and mind emerges from our brain, which can be considered that the mind is the software that runs in the brain, the hardware. Can something that makes the mind change the brain? He specifically wondered if meditation can change the brain. The existing paradigm in neuroscience has been that our brains are only malleable in childhood, very little neuroplasticity exists in adulthood. So all the neuroscientists said the answer was no. But now we 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 brain imaging of advanced meditators, including Tibetan colleagues of the Dalai Lama.
So I asked “I don’t have a professional background in neuroscience, but I’m fairly well-read in it as a hobby. I’d like to know the history of developments in understanding neuroplasticity since the 1990s: This led to a pleasant exchange in which I learned quite a bit, which I’ve shared here.
I’ll be following up with weekly posts on areas of healthy aging, both physical and mental, that I’ve researched with Gemini. I will always make sure to give AI credit. I don’t like it when people create blog posts or youtube videos with AI and don’t recognize it. I think it’s like cheating on your homework!
Share this:
Related
Posted by
I am a Mechanical Engineer born in 1953, Ph. D, Stanford, 1980. I have been in the CAE engineering field for decades. I also have a lifelong interest in outdoor activities and fitness. I have had both hips replaced and a heart valve replaced due to a genetic condition. This blog chronicles my adventures in staying active despite these bumps in the road. View all posts by BionicOldGuy
It was published
