[zeven7]

This seems like a good, simple example of complete BS:

> How many words are in this sentence?

> ChatGP: Nine words.

> List the words

> ChatGPT: How, many, words, are, in, this, sentence?

> Please count the words in the list

> ChatGPT: Seven words.

> Is that what you said before?

> ChatGPT: No, I previously said "Nine words." when counting the number of words in the sentence "How many words are in this sentence?"

> Which answer is correct?

> ChatGPT: Both answers are correct. The sentence "How many words are in this sentence?" has nine words, and the list "How, many, words, are, in, this, sentence?" has seven words.

> How can the sentence and the list from the sentence have different numbers of words?

> ChatGPT: The sentence "How many words are in this sentence?" and the list "How, many, words, are, in, this, sentence?" have different numbers of words because the sentence is a complete thought in natural language, while the list is a representation of the individual words that make up the sentence separated by commas. In the sentence, there are nine words connected by grammatical rules to form a coherent message. In the list, the words are separated and listed one by one, so each word is counted as one item in the list.

[Shocka1]

This reminds me of when I asked ChatGPT to construct a simple encryption scheme that increments each letter by one character:

A = B

B = C

...

Z = A

After explicit instructions were given and repeated back to me, I asked it to encrypt several 5 to 10 word sentences, which it consistently screwed up. Not terribly, but one or two words max, with no particular pattern that I could immediately see. I pointed out the issue and tried getting it to adjust to the correct answer, but it kept insisting that it was correct. I gave up soon after.