AI doesn’t have a mind to do mental leaps, it only knows syntax. Just a form of syntax so, so advanced that it sometimes accidentally gets things factually correct. Sometimes.
It’s more advanced than just syntax. It should be able to understand the double meanings behind riddles. Or at the very least, that books don’t have scales, even if it doesn’t understand that the scales that a piano has aren’t the same as the ones a fish has.
It doesn’t understand anything. It predicts a word based on previous words - this is why I called it syntax. If you imagine a huge and vastly complicated series of rules about how likely one word is to follow up to, say, 1000 others… That’s an LLM.
It can predict that the word “scales” is unlikely to appear near “books”. Do you understand what I mean now? Sorry, neural networks can’t understand things. Can you make predictions based on what senses you received now?
Well given that an LLM produced the nonsense riddle above, obviously it cannot predict that. It can predict the structure of a riddle perfectly well, it can even get the rhyming right! But the extra layer of meaning involved in a riddle is beyond what LLMs are able to do at the moment. At least, all of them that I’ve seen - they all seem to fall flat with this level of abstraction.
It shows that one failed that time. I just asked ChatGPT. I can’t be sure how original the riddle is. It’s possible it copied the description of the double meaning from somewhere. But it looks like it understood it, and based on how LLMs work, there’s no reason it shouldn’t.
Make an original riddle. Explain the double meaning behind it.
Riddle:
I hold many keys, yet open no doors.
I sing without voice, yet keep perfect scores.
Though I’m struck, I never feel pain;
What am I, in sun or rain?
Answer: A piano.
Explanation of Double Meaning:
Literal Interpretation
“Hold many keys, yet open no doors” refers to the piano's keyboard, which holds musical keys instead of physical keys for doors.
“Sing without voice, yet keep perfect scores” alludes to how a piano produces sound through musical notes (without a voice) and follows written scores (musical notation).
“Though I’m struck, I never feel pain” describes how piano strings are struck by hammers to create sound, but, of course, the piano doesn’t feel.
Play on Words
Keys are often associated with doors, but here, they reference musical notes.
Scores traditionally refer to results or outcomes, but in this context, they represent musical compositions.
Struck typically implies being hit and possibly feeling pain, yet here, it refers to the mechanical action within a piano that produces music.
Each line has a figurative layer connected to musical terms, creating a double meaning based on the dual use of “keys,” “scores,” and “struck.”
@Archpawn@BluesF I once asked an AI to write me the Hermione Ship of Theseus, and it was a gloriously twisted thing that veered between philosophy 101 and surrealist fanfic.
AI doesn’t have a mind to do mental leaps, it only knows syntax. Just a form of syntax so, so advanced that it sometimes accidentally gets things factually correct. Sometimes.
It’s more advanced than just syntax. It should be able to understand the double meanings behind riddles. Or at the very least, that books don’t have scales, even if it doesn’t understand that the scales that a piano has aren’t the same as the ones a fish has.
It doesn’t understand anything. It predicts a word based on previous words - this is why I called it syntax. If you imagine a huge and vastly complicated series of rules about how likely one word is to follow up to, say, 1000 others… That’s an LLM.
It can predict that the word “scales” is unlikely to appear near “books”. Do you understand what I mean now? Sorry, neural networks can’t understand things. Can you make predictions based on what senses you received now?
Well given that an LLM produced the nonsense riddle above, obviously it cannot predict that. It can predict the structure of a riddle perfectly well, it can even get the rhyming right! But the extra layer of meaning involved in a riddle is beyond what LLMs are able to do at the moment. At least, all of them that I’ve seen - they all seem to fall flat with this level of abstraction.
It shows that one failed that time. I just asked ChatGPT. I can’t be sure how original the riddle is. It’s possible it copied the description of the double meaning from somewhere. But it looks like it understood it, and based on how LLMs work, there’s no reason it shouldn’t.
Make an original riddle. Explain the double meaning behind it.
Riddle: I hold many keys, yet open no doors. I sing without voice, yet keep perfect scores. Though I’m struck, I never feel pain; What am I, in sun or rain?
Answer: A piano.
Explanation of Double Meaning:
Each line has a figurative layer connected to musical terms, creating a double meaning based on the dual use of “keys,” “scores,” and “struck.”
@Archpawn @BluesF I once asked an AI to write me the Hermione Ship of Theseus, and it was a gloriously twisted thing that veered between philosophy 101 and surrealist fanfic.