Andrej Karpathy on X: "This tweet went wide, thought I'd post some of the recent supporting articles that inspired it. 1/ GPT-3 paper showed that LLMs perform in-context learning, and can be "programmed" inside the prompt with input:output examples to perform diverse tasks https://t.co/HhrwtYNTOd"

Conversation

This tweet went wide, thought I'd post some of the recent supporting articles that inspired it. 1/ GPT-3 paper showed that LLMs perform in-context learning, and can be "programmed" inside the prompt with input:output examples to perform diverse tasks arxiv.org/abs/2005.14165
5:56 PM · Feb 19, 2023
217.2K
Views