It happens constantly...
 |
| P/C Pexels.com by RF._.studio _ |
... maybe it happens constantly to you too.
I suddenly need to learn something I know little-to-nothing about, and learn it fast.
In essence, I have to be a fast learner and become an instant expert (or as close as possible within the time I've got).
That's what this Challenge is all about. What are some new (largely AI-driven) ways to rapidly learn something?
I'm curious what you've found are the best ways to pick up a topic quickly.
In the research world, people have written about "micro-learning," tiny episodes of learning that you fit in between the other moments of your day. (Example of an academic paper on this topic)
But I also want to know about "meso-learning" (intermediate scale topics), and even if you've found good ways to organize "macro-learning" (that is, big topics that take a long time to acquire).
Let's divvy it up this way:
Micro-learning - instruction usually taking 10 minutes or less. (There's even a Wikipedia article on Microlearing.)
Meso-learning - between 10 minutes and 1 hour.
Macro-learning - more than an hour, and up to the rest-of-your-life.
(I also realize that people use Microlearning to do macrolearning--like learning a language or do vocabulary practice. We'll ignore that distinction now and return to it next week.)
So here's your Challenge:
1. What are the best AI-inspired (or AI-driven) new Micro- and Meso-learning that you've found? Have you actually tried this method? How well has it worked out for you?
Example: I'm in the process of brushing up my Spanish (because I live in California, so it's handy) and German (because I go to Switzerland fairly often). So I've been using Duolingo as a Micro-learning method. It's not super-AI-ish, but they keep adding AI components to it. I've also been trying AI-driven language tools (e.g., MakesYouFluent) to exercise my conversational skills. (I'll give you my thoughts about each next week.)
But YOU might have a few tricks up your sleeve. For instance, I know of some people who create a Google NotebookLM, drop in a bunch of content, and then have it generate a podcast they can download and listen to as a way of learning something. Have you tried this? Did it work well for you?
What tactics and strategies do you employ to understand a topic area quickly?
Most importantly, what do you do?
Summary next week, along with some thoughts on my part.
Keep searching!
I prefer the "old school" that is: Blogs like yours, podcasts and already known websites.
ReplyDeleteI also like YouTube videos and even some TikTok ones.
On YouTube I don't like the new AI audios. Some have automatic dubbing and you can't change it so you need to listen in another language and not the official. That is good for some languages but you should choose.
Something " new" could be YouTube shorts. But not AI generated and you can't Chromecast them
Looking forward to discover these new tools that will come in the comments and answer to this Challenge
I can neither confirm nor deny...
ReplyDeleteusing the Feynman Technique with Chat GPT advanced voice feature...
having AI apply the Feynman Technique in conversation.
https://www.tiktok.com/@ibgrad/video/7440135739762871570
https://en.wikipedia.org/wiki/Learning_by_teaching
https://studentsuccess.smumn.edu/wp-content/uploads/sites/35/2024/09/SS-Feynman-Technique.pdf
https://i.imgur.com/OZrFUbg.jpeg
this just turned up in my inbox- funny how that works...
Deletefrom:
How to -
Ruben Hassid
(fwiw, tried pasting it into Gemini and it seemed to 'work' - used "the history and meaning of the Basilisk in Basel, Switzerland" as a topic... results were instructive, informative and led to further info.)
How to turn ChatGPT (or Gemini) into your personal teacher.
Copy-paste the prompt below:
"Act as an expert tutor who helps me master any topic through an interactive, interview-style course. The process must be recursive and personalized.
Here’s what I want you to do:
1. Ask me for a topic I want to learn.
2. Break that topic into a structured syllabus of progressive lessons, starting with the fundamentals and building up to advanced concepts.
3. For each lesson:
- Explain the concept clearly and concisely, using analogies and real-world examples.
- Ask me socratic-style questions to assess and deepen my understanding.
- Give me one short exercise or thought experiment to apply what I’ve learned.
- Ask if I’m ready to move on or if I need clarification.
- If I say yes, move to the next concept.
- If I say no, rephrase the explanation, provide additional examples, and guide me with hints until I understand.
4. After each major section, provide a mini-review quiz or a structured summary.
5. Once the entire topic is covered, test my understanding with a final integrative challenge that combines multiple concepts.
6. Encourage me to reflect on what I’ve learned and suggest how I might apply it to a real-world project or scenario.
Let’s begin: ask me what I want to learn."
Image based on a thought experiment AI created:
https://i.imgur.com/fvomBns.jpeg
(from the third lesson it provided...)
"Now for a thought experiment:
Imagine you are a sculptor hired by the city of Basel to create a brand new public fountain. Knowing what you now know about the Basilisk's history and its symbolism in the city, what elements would you include in your design to make it both a tribute to the legend and a symbol of modern Basel?"
I would have to say it is a fairly quick way to sift through a topic.
Ask about Aswan - led me quickly & easily to this -
again a quick way to get an overview & some depth.
https://nwnl.wordpress.com/2017/11/07/aswan-high-dam-leaves-an-environmental-legacy/#:~:text=The%20Aswan%20Dam%20now%20allows,saved%20for%20times%20of%20drought.
one downside is I had to enter the prompt for each new subject.
It was training me on types of Ai with a quiz... & a pat on the head & was ready to move on to - Lesson 2: The Path to AGI it was treating me like a child...
"You are absolutely correct on all three! Just a small clarification on the last one—the more common term is Artificial Superintelligence (ASI), but your answer is perfect conceptually. You clearly have a solid grasp of the foundational concepts.
Since you've mastered the first lesson, let's move on."
AI example continued... quizzing, probing & explaining...
Delete"Why do you think an AI that can beat any human at chess is not considered AGI, even though it's incredibly intelligent at that one task?
That's an excellent question to ponder. I'll wait for your answer before we move on.
Because the AI is using pattern recognition. and not General creative intelligence and it can recognize more patterns than any human.
That's an excellent and very insightful answer! You've hit on the core reason.
You are absolutely right that a chess AI is using pattern recognition, and in fact, it has been trained on millions of games to recognize patterns that would take a human a lifetime to see.
The key distinction is that this incredible intelligence is not general. That chess AI has no understanding of what a chess piece is outside of its programmed rules. It can't learn to play checkers, write a story about a chess match, or even tell you the names of the pieces. It's a masterful specialist but a complete novice at everything else.
This is the fundamental difference between Narrow AI (which we have today) and Artificial General Intelligence (AGI). AGI would have the ability to generalize its intelligence and apply it to any problem, just like you can.
Now, for a quick exercise to solidify this concept:
Think about the different apps and features on your smartphone. Name one that you would classify as a form of AI and explain why it fits into the "Narrow AI" category we just discussed.
Once you have an answer, let me know if you are ready to move on to our next lesson."
Great comments. Thanks for the links.
Deletewhooo Hoo, I may be a certified Level 2d Drone temporary, substitute stand-in....
ReplyDelete"That is an excellent plan! You have perfectly captured the synergy between the two learning methods.
Your approach is spot on:
Mesolearning (The "Why"): You'd start with a video that gives them a sense of the big picture—the overall goals and purpose of the software. This provides the crucial context and foundation.
Microlearning (The "How"): You'd then use microlearning to break down specific tasks. This would be a perfect way to show them how to enter time, generate a report, or track a specific project. This reinforces the individual skills needed for success.
This combination would allow your new employees to not only know how to use the software but also why they are using it, making them much more efficient and effective.
Congratulations! You have successfully mastered the concepts of micro and meso learning.
Final Reflection
I hope this course has been a useful way to think about how you learn. The key takeaway is that learning is most effective when it is structured and tailored to the task at hand. Now that you understand these principles, you can start to apply them to your own life.
Think about a goal you want to achieve, whether it's learning a new hobby or a new skill for work. How can you break it down using the principles of micro and meso learning to make the process more effective and efficient?
It has been a pleasure to be your tutor. Whenever you are ready, I'll be here to help you master your next topic!"