
73: Consequences of Language (with Nick Enfield and Morten Christiansen)
Because Language - a podcast about linguistics, the science of language.
00:00
Large Language Models Can Learn to Make Grammatical Output
Large language models are capable of learning to make grammatical output just by looking at linguistic input alone. So what these models do simply is given a past input try to predict what's the next probable word to occur. But it'd be fair to say that large language models are spicy auto-complete on steroids. Yes.
Transcript
Play full episode