If I program something to always reply “2” when you ask it “how many [thing] in [thing]?” It’s not really good at counting. Could it be good? Sure. But that’s not what it was designed to do.
Similarly, LLMs were not designed to count things. So it’s unsurprising when they get such an answer wrong.
Assume it is not. If you’re asking an LLM for information you don’t understand, you’re going to have a bad time. It’s not a learning tool, and using it as such is a terrible idea.
If you want to use it for search, don’t just take it at face value. Click into its sources, and verify the information.
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?
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.
On the top, a bright, clear sunny day, a few picturesque clouds in the sky.
At the bottom, a river, once clean, where corporate logos such as Google and Microsoft sit, partially submerged, stains spreading into the waters around them.
In the middle, a bridge: well constructed across and overtop the river, across which various Fediverse logos are crossing
lemmy.world
Hot