Hacker News new | ask | show | jobs
by iliane5 1107 days ago
> LLMs are not particularly good at arithmetic, counting syllables, or recognizing haikus

I suspect most of this is due to tokenization making it difficult to generalize these concepts.

There are some weird edge cases though, for example GPT-4 will almost always be able to add two 40 digits number but it is also almost always wrong when adding a 40 digit and 35 digit number.
2 comments
rcme 1107 days ago
It doesn't have anything to do with tokenization. You can define binary addition using symbols, e.g. a and b, and provide properly tokenized strings to GPT-4. GPT-4 appears to solve the arithmetic puzzles for a few bits, but quickly falls apart on larger examples.
link
iliane5 1107 days ago
What I was saying is that because you need to go out of your way to make sure it's tokenized properly, I wouldn't be surprised if there are enough non properly tokenized examples in the dataset.

If that was the case, it would make it difficult to generalize these concepts.

link
doctor_eval 1107 days ago
Could it also be that syllables are intrinsically mechanical? They are strongly related to how our mouths work. While it may be possible to extract syllables from written text - following the consonants and vowels - I'm not sure that many humans could easily count syllables without using their mouths.
link
aidenn0 1107 days ago
Many humans are also often really bad at doing speech related things when writing.

I've known many native English speakers who write things like "an healthy" (because they learned to write "an" before words starting with "h") and write poems that don't rhyme because the words end with the same letters (e.g. "most" and "cost").

link
doctor_eval 1107 days ago
Yeah, I find it weird how LLMs make a lot of the kind of mistakes that people do, but somehow this is held up as being a reason why LLMs don’t work similarly to brains.

Since discovering LLMs I’ve become convinced that my brain works like them. I really don’t know the next word I’m going to say until it’s nearly out. And since learning about how LLMs work, I really can’t argue it away.

It’s a reasonably disturbing feeling.

link