videoplayback
Peatükid
-
0:00Peatükk 1: Hi, everyone. 299s · Speaker 2
Hi, everyone. So in this video, I would like to continue our general audience series on large language models like ChatGPT. Now, in a previous video, deep dive into LLMs that you can find on my YouTube, we went into a lot of the under -the …
-
5:00Peatükk 2: So we said 15 tokens and it said 19 tokens back. 302s · Speaker 2
So we said 15 tokens and it said 19 tokens back. Now, because this is a conversation and we want to actually maintain a lot of the metadata that actually makes up a conversation object, this is not all that's going on under the hood. And we…
-
10:03Peatükk 3: Now, some knowledge can come into the model through the post -training phase, which we'll talk about in a second. 300s · Speaker 1
Now, some knowledge can come into the model through the post -training phase, which we'll talk about in a second. But roughly speaking, you should think of these models as kind of like a little bit out of date because pre -training is way t…
-
15:04Peatükk 4: whether or not they helped mitigate running nose. 77s · Speaker 2
whether or not they helped mitigate running nose. Now, when these ingredients are coming here, again, remember, we are talking to a zip file that has a recollection of the internet. I'm not guaranteed that these ingredients are correct. And…
-
16:22Peatükk 5: Okay, so at this point, I want to make two nodes. 301s · Speaker 1
Okay, so at this point, I want to make two nodes. The first note I want to make is that naturally as you interact with these models, you'll see that your conversations are growing longer, right? Anytime you are switching topic, I encourage …
-
21:23Peatükk 6: I was asking for just travel advice. 300s · Speaker 2
I was asking for just travel advice. So I was asking for a cool city to go to. And Claude told me that Zermatt in Switzerland is really cool. So I ended up going there for a New Year's break following Claude's advice. But this is just an ex…
-
26:24Peatükk 7: I turned to one of the thinking models. 275s · Speaker 1
I turned to one of the thinking models. Now, for OpenAI, all of these models that start with O are thinking models. O1, O3 Mini, O3 Mini High, and O1 Pro, Pro Mode, are all thinking models. And they're not very good at naming their models, …
-
31:00
Okay, now the next section I want to continue to is to tool use. So far, we've only talked to the language model through text. And this language model is, again, this zip file in a folder. It's inert. It's closed off. It's got no tools. It'…
-
36:00Peatükk 9: and so I would just select search. 303s · Speaker 1
and so I would just select search. But let's see first, let's see what happens. Okay, searching the web, and then it prints stuff, and then it cites. So the model actually detected itself that it needs to search the web because it understan…
-
41:03
Has Brian Johnson talked about the toothpaste he uses? And I was curious basically like what Brian does. And again, it has the two features. Number one, it's a little bit esoteric. So I'm not 100 % sure if this is at scale on the internet a…
-
42:04Peatükk 11: Okay, next up, I would like to tell you about this capability called Deep Research. 300s · Speaker 2
Okay, next up, I would like to tell you about this capability called Deep Research. And this is fairly recent, only as of like a month or two ago. But I think it's incredibly cool and really interesting and kind of went under the radar for …
-
47:04Peatükk 12: Let's see if Perplexity finished. 301s · Speaker 1
Let's see if Perplexity finished. Okay, Perplexity is still researching and ChatGPT is also researching. So let's briefly pause the video and I'll come back when this is done. Okay, so Perplexity finished and we can see some of the report t…
-
52:05Peatükk 13: other thinking models were produced. 300s · Speaker 1
other thinking models were produced. So what we can do now is we can upload the documents that we wanted to reference inside its context window. So as an example, there's this paper that came out that I was kind of interested in. It's from …
-
57:06Peatükk 14: And then what I do here is I copy paste. 184s · Speaker 1
And then what I do here is I copy paste. Now in Claude, when you copy paste, they don't actually show all the text inside the text box. They create a little text attachment when it is over some size. And so we can click enter. And we just k…
-
1:00:11Peatükk 15: Okay, so LLM did exactly what I just did. 302s · Speaker 2
Okay, so LLM did exactly what I just did. It calculated the result of the multiplication to be 270. But it's actually not really doing math. It's actually more like almost memory work. But it's easy enough to do in your head. So there was n…
-
1:05:14Peatükk 16: I wanted to actually look it up and back it up and create a table where each year we have the valuation. 300s · Speaker 1
I wanted to actually look it up and back it up and create a table where each year we have the valuation. So these are the OpenAI valuations over time. Notice how in 2015, it's not applicable. So the valuation is like unknown. Then I set now…
-
1:10:14Peatükk 17: And that looks like this. 302s · Speaker 1
And that looks like this. So what Claude wrote specifically was this code here. So it uses a React library and then basically creates all these components. It hardcodes the Q &A into this app. And then all the other functionality of it. And…
-
1:15:16
and then it works with those files and edits them with you. So the way this looks is as follows. Here I have a simple example of a React app that I built over a few minutes with Cursor. And under the hood, cursor is using Claude 3 .7 Sonnet…
-
1:20:16
But every time it saves a file, we actually are deploying it. So we can actually try to refresh and just see what we have right now. Oh, so it added a new effect. You see how it kind of fades in, which is kind of cool. And now we'll win. Wh…
-
1:25:17Peatükk 20: So you can bind a key that you want to use for that. 77s · Speaker 2
So you can bind a key that you want to use for that. So for example, I use F5. So whenever I press F5, it will listen to me, then I can say stuff, and then I press F5 again, and it will transcribe it into text. So let me show you. I'll pres…
-
1:26:35Peatükk 21: Okay, so I'll stop it. 122s · Speaker 3
Okay, so I'll stop it. So different apps like ChatGPT or Cloud or Gemini or whatever you are using may or may not have this functionality, but it's something you can definitely look for. When you have the input be system -wide, you can, of …
-
1:28:37
chunks. And then you actually train the model with these audio chunks so that it can actually understand those little pieces of audio. And this gives the model a lot of capabilities that you would never get with this fake audio, as we've ta…
-
1:29:39Peatükk 23: Andre, I'm doing great. 72s · Speaker 3
Andre, I'm doing great. How about you? I'm great. I'm wondering why the sky is blue. Is it because it's reflecting the ocean? Glad to hear you're great. Actually, the sky is blue because of a phenomenon called Rayleigh scattering. Okay, oka…
-
1:30:51Peatükk 24: Okay, hold on. 198s · Speaker 6
Okay, hold on. Can you please count from 1 to 10 and do it very, very fast? Sure. 1, 2, 3, 4, 5, 6, 7, 8, 9, 10. Okay, that wasn't fast enough. Do it from 1 to 20 and do it even faster. All right. 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, …
-
1:34:09Peatükk 25: Hey, I'm great. 303s · Speaker 4
Hey, I'm great. Which mode do you recommend we try out? Alright, that sounds great. I'm gonna try out the romantic mode. Okay, hello? I hope I'm not bothering you. I just, I wanted to talk to you. I've always admired you from afar. You alwa…
-
1:39:13
some documents or topics or papers that I'm not usually an expert in and I just kind of have a passive interest in and I'm going out for a walk or I'm going out for a long drive and I want to have a custom podcast on that topic. And so I fi…
-
1:40:19Peatükk 27: column. Okay, next up, what I want to turn to is images. 300s · Speaker 2
column. Okay, next up, what I want to turn to is images. So just like audio, it turns out that you can re -represent images in tokens. and we can represent images as token streams, and we can get language models to model them in the same wa…
-
1:45:19
I asked for it in text because then I can copy this text and I can ask a model what it thinks the value of x is evaluated at pi or something like that it's a trick question you can try it yourself Next example, here I had a Colgate toothpas…
-
1:50:06Peatükk 29: Okay, well, let's look at this. 300s · Speaker 3
Okay, well, let's look at this. What book is this? Do you know? Yes, that's Genghis Khan and the Making of the Modern World by Jack Weatherford. It's a fascinating book about the impact of Genghis Khan on world history. Yeah, very good. Do …
-
1:55:06Peatükk 30: There we go. 301s · Speaker 2
There we go. So you see this memory updated. Believes that late 1990s and early 2000s was the greatest peak of Hollywood, etc. Yeah. So, and then it also went on a bit about 1970. And then it allows you to manage memories. So we'll look int…
-
2:00:08
i give instructions to llms i always like to number one give it sort of the description but then also give it examples so i like to give concrete examples And so here are four concrete examples. And so what I'm doing here really is I'm cons…
-
2:01:39Peatükk 32: So, as an example, I have this sentence in Korean, and I want to know what it means. 301s · Speaker 2
So, as an example, I have this sentence in Korean, and I want to know what it means. Now, many people will go to just Google Translate or something like that. Now, famously, Google Translate is not very good with Korean, so a lot of people …
-
2:06:40Peatükk 33: what people are introducing, and what to look out for. 270s · Speaker 1
what people are introducing, and what to look out for. So, in summary, there is a rapidly growing, changing and shifting and thriving ecosystem of LLM apps like ChatGPT. ChatGPT is the first and the incumbent and is probably the most featur…