yego.me
💡 Stop wasting time. Read Youtube instead of watch. Download Chrome Extension

How AI, Like ChatGPT, *Really* Learns


2m read
·Nov 7, 2024

The main video is talking about a genetic breeding model of how to make machines learn. This method is simpler to explain or just show. Here is a machine learning to walk, or play Mario, or jump really high. A genetic code is an older code, but it still checks out, and I personally suspect in the future genetic models will have a resurgence as compute power approaches crazy pants.

However, the current hotness is deep learning and recursive neural networks, and that is where the linear algebra really increases and explainability in a brief video really decreases. But if I had to kind of explain how they work in a footnote, just for the record, it's like this: No infinite warehouse. Just one student. Teacher Bot has the same test, but this time Builder Bot is 'Dial Adjustment Bot,' where each dial is how sensitive one connection in the student bot's head is.

There's a lot of connections in its head, so a lot of dials. A LOT, a lot. Teacher Bot shows Student Bot a photo, and Dial Adjustment Bot adjusts that dial stronger or weaker to get Student Bot closer to the answer. It's a bit like adjusting the dial on a radio. Is that still a thing? Do cars have radios still? I don't know, anyway.

You might not know the exact frequency of the station, but you can tell if you're getting closer or further away. It's like that but with a hundred thousand dials and a lot of math, and that's just for one test question. When Teacher Bot introduces the next photo, Dial Adjustment Bot needs to adjust all the dials so that Student Bot can answer both questions. As the test gets longer, this becomes an insane amount of math and fine-tuning for Dial Adjustment Bot.

But when it's done, there's a student bot who can do a pretty good job at recognizing new photos, though still suffers from some of the problems mentioned in the main video. Anyway, that's the most babies' first introduction to neural networks you will ever hear. If it sounds interesting to you and you like math and code, go dig into the details; machines that learn are the future of everything.

Maybe, quite literally, the future of everything, and given what we've put them through, may the bots have mercy on us all.

More Articles

View All
Photosynthesis in ecosystems | Middle school biology | Khan Academy
When you look at a rain forest ecosystem like this, one of the obvious questions may be: where do these plants come from? How do they grow? They’re growing all the time, getting larger and larger and larger. Where does that mass, where does that matter co…
Dr. Martin Luther King Jr.'s Sermon | Genius: MLK/X | National Geographic
♫ Oh, teach me what to say. ♫ Good morning. Good morning. I had another sermon I intended to preach to you today. One that encompassed all that I have learned in my many, many years of education and preaching at my father’s hip. [Congregation] Yes. Yes. …
What is mastery learning?
[Narrator] Have you ever really tried to learn something and you just couldn’t? It can make you feel like you’re not so smart, right? Well, it’s not your fault and it’s not your teacher’s fault, it’s just our traditional approach to learning. We go thro…
This Platform Might Be Worse Than TikTok
We’ve talked extensively about the dangers of Tick Tock, but what if I told you that Snapchat was way more dangerous? While Tick Tock’s influence is more subtle in psychological terms, Snapchat puts young people at immediate, sometimes life-threatening ri…
Sharing is Caring | Live Free or Die
Are you clearing a path for me? Yeah, thank you. All right, I’m coming through. Work on this piece over here in the Blue Ridge Mountains. Taming their 1-acre hillside property by hand is a non-stop project for Tony and Amelia. “Boom shakalaka! Boom shak…
Graphing logarithmic functions (example 2) | Algebra 2 | Khan Academy
This is a screenshot from an exercise on Khan Academy. It says the interactive graph below contains the graph of y is equal to log base 2 of x as a dashed curve, and you can see it down there is that dashed curve with the points (1, 0) and (2, 1) highligh…