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
A Woman's Epic Journey to Climb 7 Mountains—Shot on a Phone | Short Film Showcase
Oh general dishy, or would boo be true! She should tie a me. Who dat? ACK. No tuna can to de shanty Shuler G. Ida, by dunya PHP. Know him elections for she, we Bishop targeted Jahida. I mean, cooling it. I’m not, don’t worry. And tonight he should be th…
Warren Buffett's Stark Warning About 'AI Stocks'
We let a genie out of a bottle when we develop nuclear weapons, and AI is somewhat similar. All right team, we’ve got a lot more to talk about. As you guys would have seen in my last video, I am here in Omaha covering the Berkshire Hathaway shareholder m…
Here’s EXACTLY how much I made from YouTube in 2018 (Not Clickbait)
What’s up, you guys? It’s Graham here. So I’ll just get right into it. A month ago, I posted a video showing how much I made from a 1.4 million view viral video, which if you haven’t seen that video yet, make sure to go and check that out so you can go an…
Startup Experts Reveal Their Top Productivity Advice
A lot of people think that they’re great at multitasking, and they are not. I think the best Founders, you’ll see them be very picky with their time, and sometimes it’s the non-obvious things that end up being the things that really unlock your business. …
Tax implications of non-typical pay structures | Employment | Financial Literacy | Khan Academy
So let’s think about some of the pros and cons of self-employment. I’m going to make a column of pros and then in cons maybe a nice scary red over here. Alright, cons. I think a lot of folks, when they imagine working for themselves, they imagine, “Well…
How to Identify a Bull Shark | Raging Bull Shark
NARRATOR: Researchers have confirmed 100 bull shark attacks. But the real number may be much higher because the bull shark is so difficult to identify. When you first look at a bull shark, it doesn’t really jump out at you that it’s a bull shark. It just …