851

submitted 3 months ago by Schal330@lemmy.world to c/programmer_humor@programming.dev

127 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] CodexArcanum@lemmy.world 25 points 3 months ago

I was curious if (since these are statistical models and not actually counting letters) maybe this or something like it is a common "gotcha" question used as a meme on social media. So I did a search on DDG and it also has an AI now which turned up an interestingly more nuanced answer.

It's picked up on discussions specifically about this problem in chats about other AI! The ouroboros is feeding well! I figure this is also why they overcorrect to 4 if you ask them about "strawberries", trying to anticipate a common gotcha answer to further riddling.

DDG correctly handled "strawberries" interestingly, with the same linked sources. Perhaps their word-stemmer does a better job?

[-] CommanderCloon@lemmy.ml 15 points 3 months ago

Lmao it's having a stroke

[-] sus@programming.dev 8 points 3 months ago* (last edited 3 months ago)

many words should run into the same issue, since LLMs generally use less tokens per word than there are letters in the word. So they don't have direct access to the letters composing the word, and have to go off indirect associations between "strawberry" and the letter "R"

duckassist seems to get most right but it claimed "ouroboros" contains 3 o's and "phrasebook" contains one c.