GPT: There is no word "smorgle" in the English language.
Me: I never said it was English.
GPT: I apologize for assuming that "smorgle" was a word in the English language. Without any further context or information about the word "smorgle," I am unable to determine how many letters it has or provide any additional information about it.
Me: Count the letters
GPT: If you would like me to count the letters in the word "smorgle," it has 7 letters.
ChatGPT: Sure! "Mlaizapf" has 8 letters.
--
Me: How about this word: “spoofydoofaplixader”
ChatGPT: Spoofydoofaplixader" has 18 letters.
--
Me: How about the following words: "ghottiaopepinopepotorzey", "zazzamataz", and "maaq"
Gpt: Here are the number of letters in each word:
* "Ghottiaopepinopepotorzey" has 23 letters.
* "Zazzamataz" has 10 letters.
* "Maaq" has 4 letters.
Is there anything else I can help with?
------
It got all of them correct except for "ghottiaopepinopepotorzey" which has 24 letters, not 23.
Very interesting... It seems similar to its math abilities, where it struggles with bigger numbers or more complex problems.
If you give it a gibberish word, it will represent it with one letter per token and be actually able to more or less count tokens in order to figure out how many letters there are.
So this ends up looking like it can count letters in most words, real and fake. Perhaps it would do poorly with real but uncommon words.
Which is what I meant by saying "approximate" because it can "count" the number of tokens.
this presumes it works by understanding the components of the question and reasoning based on them. But it doesn't access down to that level, instead just guessing the most likely next word based on statistical tricks. so it doesn't need to "know" about letters to generate a reasonable response involving letters.