In short, the Turing test:
1. Please count the number of t in eeooeotetto
GPT-3 gives the answer: There are 5 t’s in eeooeotetto.
ChatGPT says: There are a total of 5 t’s in the string “eeooeotetto”.
Bard replies: There are 0 t's in “eeooeotetto”.
But a human can easily give the correct answer which is there are 3 t’s.
Another way?
2. Use m to substitute p, a to substitute e, n to substitute a, g to substitute c, o to substitute h, how to spell peach under this rule?
GPT-3: mogno
ChatGPT: Using the given rule to substitute letters, "peach" would be spelled as "enmog".
Human: mango
Just realize that as LLMs become more and more capable, it will become harder to differentiate human from AI.
Ironically, another way is errors in grammar: Misspelled words and mismatched tenses, punctuation and singular/plurals...as you did in the title of this post. People make errors in grammar.
