The “T” in ChatGPT stands for Transformer — from a 2017 paper about attention.

Wacky WorldAI & Computers

GPT means Generative Pre-trained Transformer. The transformer architecture was introduced by eight Google researchers in the 2017 paper “Attention Is All You Need”, now one of the most cited papers in computing.

Another wacky fact → All facts

Explore more Wacky World facts

The first program to learn to play a game improved by playing against itself — in the 1950s.The backpropagation paper that powers neural networks was barely four pages long.GPT-3 had 175 billion parameters.