Hacker News Reader

Comment by anonzzzies | Hacker News Reader

Yep, people find this interesting, but many (many) people get this wrong as well; it has something to do with how many letters it is and how many you can keep in your head I think. We are not very good counters or calculators or computers and, even though I am not saying llms are the same or close to humans, we tried to model their substrates after biology and are surprised we get something that cannot count or calculate very well.

I find it a dumb test that proves nothing imho.

However, not very impressed with this model.

View on HN

It's a magician-like trick. The double-r gets all the attention because one needs to consciously remember it, so nobody remembers to look at the other single-r.

The LLMs probably get it wrong because people get it wrong.

I thought it was something to do with the way tokens are generated for the word strawberry?

https://arbisoft.com/blogs/why-ll-ms-can-t-count-the-r-s-in-...

That explanation would require the LLM to actually understand the question and deriving an answer from first principles.

It doesn't.

If the input is parsed in to tokens, and the tokens split compound words, nothing about that requires "first principles" thinking to explain why LLMs struggle with getting all of the letters -- the LLM is only going down the vector path of one of the compound words...

(I don't think LLMs are sentiment or intelligent btw, I think they are giant probability machines, and the probability that the LLM will get 3 r's on a token of "berry" are very low.)

The LLM gives you the answer it finds on the training set. All the things on that article are irrelevant for the answer.

"The choice of tokenization method can directly affect the accuracy of character counting. If the tokenization method obscures the relationship between individual characters, it can be difficult for the LLM to count them accurately. For example, if "strawberry" is tokenized as "straw" and "berry," the LLM may not recognize that the two "r"s are part of the same word.

To improve character counting accuracy, LLMs may need to use more sophisticated tokenization methods, such as subword tokenization or character-level tokenization, that can preserve more information about the structure of words."

What, again, assumes the LLM understood the question and is making an answer from first principles.

No, it does not.

You said above that "The LLM gives you the answer it finds on the training set"

You and I both agree on that. No first principles there.

The training set -- how's it built? With tokens. We have not trained LLMs with a token structure that deals well with compound words.

If we trained LLMs with a different token structure, it is more probable that a one-shot answer for these compound word letter counting problems would be accurate.

The LLM does not need to understand what "counting is" or even "what a letter is". The LLM will regurgitate the token relationship we train it on.

> many (many) people get this wrong as well

Many people can't count letters in a word?

I messed up spelling "juggler" in a spelling bee once (I was 10).

The confusing thing about LLMs is that they speak tokens, not written text, so it's a lot more like interrogating someone who is functionally illiterate- of course they're going to be a terrible speller.

You can find much weirder things that LLMs are absurdly bad at, like "A farmer needs to get himself and a chicken across a river. His boat can hold the farmer and one piece of cargo. How does he do this?" 9 times out of 10 LLMs will pattern match this to the classic puzzle (there's usually also a sack of grain and a wolf) and start insisting on extra trips and inventing wolves. Even if a human makes the same mistake, they almost certainly would realize it after being reminded that there is no wolf, but LLMs often insist there is. o1-preview (but not -mini) seems to have cracked it, though.

Yep. Try it with your neighbours. It's not bad or offensive; it is just what it is.

Reply on news.ycombinator.com