The Evolution of Large Language Models

These large language models work sort of like an auto-correct on your phone keyboard. They're trained on what are likely completions of what you're typing. The leading one is called a transformer and it's designed to accuse that we develop from context. And then on top of all that, it has a fine tuning so-called procedure where not only willauto complete what you've typed in, but it'll actually try to construct a dialogue with you.