It’s a word predictor. It is good at simple text processing. Think local code refactoring, changing the style or structure of a small text piece, or summarizing small text pieces into even smaller text pieces. It is ok at synthesizing new text that has similar structure to the training corpus. Think generating repetitive boilerplate or copywriting. It is very bad at recalling or checking facts, logic, mathematics, and everything else that people seem to be using it for nowadays.