417
You got it! rule (pawb.social)
you are viewing a single comment's thread
view the rest of the comments
[-] jlow@beehaw.org 8 points 1 week ago

Classic case of "that's not what LLMs are made for"?

[-] Smorty@lemmy.blahaj.zone 3 points 1 week ago

It indeed is one of these cases. Individual letter recognition doesn't work well, since they tend to be clumped up into larger "tokens", which then can't be differentiated anymore. That's also the same reason why it can't count the letters in words, It sees words as just a single, or at most three "tokens"

[-] Swedneck@discuss.tchncs.de 1 points 2 days ago

what i don't get is that surely it must be perfectly feasible to just implement letter tracking as a separate function that the LLMs can somehow interact with? they can clearly hook up the LLMs to stuff like wikipedia for up to date information..

[-] Smorty@lemmy.blahaj.zone 1 points 2 days ago

And right again, ai enthusiasts have already hooked up LLMs to the ability to write their own code. It's infact super easy to let a model write a script which then countanthe letters.
Then again, it's also the case, that you could just use a normal program for that in the first place.

This whole "how many Rs are there in 'Strawberry' " thing is nice to show people that LLMs can't do everything. But it's also not a reasonable usecase.

You don't hire people to count words in a document, that's what computers are for.

The reason for my LLMs don't read every character individually is because it's way more efficient to let it detect entire words, rather than letters.

Building a "letter tracker" into an LLM would only be useful to specifically make these people happy, who make fun of LLMs not counting the Rs, and literally no one else...

this post was submitted on 04 Nov 2024
417 points (99.3% liked)

196

16477 readers
2159 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS