The Future of Language Models

There used to be a benchmark called GLU, which was used to measure how close the human performance those language models could get. And now there's another version that has been actually I think since last year was called superglue and it's more demanding. It's also in some funny way unsurprising in that language is so malleable and extensible, right? You know, we've used language described so many different aspects of kind of human endeavour and human knowledge. SoI think we're only going to see the kind of unusual applications of language models grow.