AI language models like GPT-3 can achieve up to 97% accuracy on some Winograd schemas, but understanding language doesn't equate to understanding the

[Techmeme]

Melanie Mitchell / Quanta Magazine:
AI language models like GPT-3 can achieve up to 97% accuracy on some Winograd schemas, but understanding language doesn't equate to understanding the world — It's simple enough for AI to seem to comprehend data, but devising a true test of a machine's knowledge has proved difficult.