Live data from Hacker News

“Don Knuth Plays with ChatGPT” but with ChatGPT-4

gist.github.com

11–20 of 141 posts

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#11
post #5

Interesting that it didn't get the 5-letter word sentence right.

Based on my experiments it usually does get it right (18 correct answers out of 20 attempts), and the failures I got were similar to this one: a single six-letter word in an otherwise correct sentence.

Sam and friends must be giggling all the way to the bank: they have a service that 'probably' gives the correct result and paying customers are happy to retry until it gets it right.

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#13
post #5

Earlier quoted context omitted.

Based on my experiments it usually does get it right (18 correct answers out of 20 attempts), and the failures I got were similar to this one: a single six-letter word in an otherwise correct sentence.

Sam and friends must be giggling all the way to the bank: they have a service that 'probably' gives the correct result and paying customers are happy to retry until it gets it right.

> Sam and friends must be giggling all the way to the bank

it's true but for another reason. they yoinked it away from the nerds who were baited to work on openai because those nerds thought how the name of the company was spelled meant something about how it would behave. it reminds me of how some act around software names like 'alpha' like it has objective meaning with consequences in reality

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#14

Interesting that it didn't get the 5-letter word sentence right.

It's fed sub-word tokens not letters (even though it can split a word into letters), and apparently struggles with counting in general. No doubt some of the things it struggles with could be improved with targeted training, but others may require architectural changes.

Imagine yourself trying to use only 5 letter words if you can't see how many letters are actually in each word, and had to rely on a hodgepodge of other means to try to figure it out!

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#15
post #6

Interesting both completely whiff on the number of chapters in the Haj.

How would you get the correct number? I just did two Google searches and can't find the correct answer anywhere in the first page of results ("Novel The Haj chapters" and "Novel The Haj chapter list"). Even looking in the "look inside" preview on the Penguin Randomhouse website doesn't help because it apparently doesn't have a table of contents. I'm not surprised ChatGPT doesn't know and to me the only bad thing is that it's hallucinating an answer instead of admitting it doesn't know.

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#16
post #5

Earlier quoted context omitted.

Based on my experiments it usually does get it right (18 correct answers out of 20 attempts), and the failures I got were similar to this one: a single six-letter word in an otherwise correct sentence.

Sam and friends must be giggling all the way to the bank: they have a service that 'probably' gives the correct result and paying customers are happy to retry until it gets it right.

"This talking dog is sort of a dumbass. I don't get the hype."

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#18
post #8

>> What is the most beautiful algorithm? > Quicksort Algorithm Definitive proof that AI must be stopped. Ranking quicksort as more elegant than heapsort?!

That is a weird way of spelling mergesort.

That is a weird way of spelling Bogo Sort.

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#19
post #8

>> What is the most beautiful algorithm? > Quicksort Algorithm Definitive proof that AI must be stopped. Ranking quicksort as more elegant than heapsort?!

That is a weird way of spelling mergesort.

I believe radix sort belongs first in this list.

Re: “Don Knuth Plays with ChatGPT” but with ChatGPT-4

#20

Earlier quoted context omitted.

Sam and friends must be giggling all the way to the bank: they have a service that 'probably' gives the correct result and paying customers are happy to retry until it gets it right.

"This talking dog is sort of a dumbass. I don't get the hype."

GPT is a wonder as technology goes; the hype is justified. I was discussing Sam's business model.
Post reply on HN