Search posts, tags, users, and pages
LLMs turn text into tokens, feed them through a Transformer's self-attention, and generate replies one token at a time — not by copying the web.
Abhijit Mone
@bloggerAbhijit · Pune
Ai Enthusiast
Markdown supported · ⌘↵ to post
Julian Neagu
I like that you kept this simple. A lot of people think the model is searching the web every time. That one idea alone clears up a lot of confusion.
Julian Neagu
I like that you kept this simple. A lot of people think the model is searching the web every time. That one idea alone clears up a lot of confusion.