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
Elon Musk $5 million donation to Khan Academy thank you
Hi everyone, Sal Khan here from Khan Academy, and I just wanted to give a huge shout out and thank you to Elon Musk and everyone at the Musk Foundation for their incredibly generous support for Khan Academy. They just recently gave a 5 million dollar don…
Steve Jobs Insult Response - Highest Quality
Yes Mr. Jobs, you’re a bright and influential man. Here it comes. It’s sad and clear that on several counts you’ve discussed, you don’t know what you’re talking about. I would like for example for you to express in clear terms how, say Java in any of its …
Why self improvement is ruining your life
One of the best feelings in the entire world is the feeling of getting better at the things that you’re interested in. You know, if you’re starting to get into the gym, it feels really good to actually see yourself getting stronger, whether that’s visuall…
How to organize your life using Notion| My Notion Tour + free templates
Hi, guys! What’s up? It’s me, Ruri. Today, I’m back with another video. So today, I’m gonna show you and explain to you my full Notion setup, what I use, how I use. So that you can start your new school year organized and everything put together, you know…
Adaptation and environmental change | Mechanisms of evolution | High school biology | Khan Academy
Hi everybody, Dr. Sammy here, your friendly neighborhood entomologist. Here to talk to you about how adaptation, which is dependent on the environment, responds in the context of environmental change. Natural selection promotes adaptation in populations. …
Approximating dividing by decimals
What we’re going to do in this video is get a little bit of practice estimating dividing with decimals. So, for example, we want to figure out approximately— that’s what these kind of squiggly equal sign means; this means approximately equal. So what is…