Guió gràfic
0:001:03
0:00
0:30
1:00
Escena
1. Títol
2. Esbós
3. Citació
4. Paraula clau
5. Esbós
6. Citació
7. Citació
Subtítol
Let’s unpack large language mode...
Think of them as systems that pr...
again and again.
First, the model reads a huge am...
That training helps it notice pa...
like how words usually fit toget...
Imagine a giant autocomplete wit...
It does not search a dictionary,
it estimates what comes next.
Inside the model are layers of
math that turn words into number...
Those numbers help it compare
ideas and connect related meanin...
When you type a prompt,
the model looks at the context a...
Then it scores many possible nex...
It repeats that step,
one token at a time,
until the reply feels complete. ...
word by word.
So the big idea is simple: a lan...
and predicts the next piece of t...
Element visual
Vídeo
Escena amb esbós
Vídeo
Vídeo
Escena amb esbós
Imatge
Vídeo
Àudio
TTS
TTS
TTS
TTS
TTS
TTS
TTS
Música
Background Music 1