Great article. It is all about how (and who) measures 'success' - in large language models (LLMs) like GPT-3 (I have a short article that talks about this here https://www.sorcero.com/blog/measuring-progress-natural-language-understanding) and a longer article in The Gradient that shows why the brute force data-driven approach will never achieve true language understanding - here https://thegradient.pub/machine-learning-wont-solve-the-natural-language-understanding-challenge/.