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
The Secret to Building Wealth Fast
What if we told you there was a way to build extreme levels of wealth incredibly fast? What if we told you that almost all self-made millionaires and billionaires have used this exact strategy to build their fortunes? And there’s nothing stopping you from…
STRAPPED INTO A SINKING HELICOPTER (with U.S. Marines) - Smarter Every Day 201
(helicopter flying) (alarm systems beeping) [Instructor] Ditching, ditching, ditching. (water rushing) So, I’m alive. (laughs) All right, here’s the deal. My last mission as a U.S. government civil servant was in a helicopter off the coast of Hawaii. W…
Bird Taking Off at 20,000 fps (213 milliseconds) - Smarter Every Day 197
Hey, it’s me, Destin. Sorry for the vertical video there. I was recording for the Instagram story. So I caught this bird with my hand, and I got to thinking about it. It’s kind of a shame to have a bird and let it go and not film it in slow motion. So, th…
Why Its Good That The Democrats Lost
I’m going to stay on this theme for a moment and call this perhaps the greatest night the Democratic party can ever have if they lose. Let me explain that I was very troubled just over a 100 days ago when they circumvented the Democratic process and anoin…
Black Holes, Blazars, and Women of Color in Science | Nat Geo Live
JEDIDAH ISLER: Studying science changed me and it allows me to make contributions into the world. And everyone, regardless of their identity, should have that right. We cannot get to the best possible exploration, whether it’s on this planet or beyond, if…
Phototropism | Plant Biology | Khan Academy
You’ve probably seen plants either in your house or, if you go for a walk, you’ve seen parts of the plants twist and turn in all sorts of directions. If you observe closely, you’ll see that oftentimes it looks like the plant is twisting or turning towards…