News for hackers. Stuff that matters.
Re:I Asked ChatGPT to Explain Some Jokes to Me by visarga on Saturday December 17, 2022 @11:25AM (#34029170)
I think the latest GPT-3 can spell and get the joke.

Explain this: "no pun in ten did"

text-davinci-003: This phrase is a play on words. It is a way of saying that no pun was intended, or that the speaker did not intend to make a joke.

Write letter by letter "no pun in ten did"

text-davinci-003: n o p u n i n t e n d i d

Re:I Asked ChatGPT to Explain Some Jokes to Me by mewpmewp2 on Saturday December 17, 2022 @03:24PM (#34031858)
Maybe it has trained to have connections like no => pun => in => ten => did => "joke, on 'no pun was intended'".

In this case I wouldn't say it got the joke, but it's just memorised that this popular order of words would be this particular joke. I wonder if you change the order os somehow tweak the joke a bit so it would be something that shouldn't be in the training data?

Re:I Asked ChatGPT to Explain Some Jokes to Me by visarga on Sunday December 18, 2022 @03:14AM (#34035894)
I think you're right, the exact phrase appears 130K times in Google.

But it can spell any word. I tested both in text-davinvi-003 and chatGPT, both initially refused to spell the garbage word "khfsihciweb" but after insisting they did it.

It can even invent readings for acronyms that don't exist:

Acronym: CNN

Expand: Convolutional Neural Network

Acronym: PNP

Expand: Plug and Play

Acronym: SHDJ

Expand: Super High-Definition Jukebox

Acronym: HEDUE

Expand: Higher Education Digital User Experience

Acronym: SHADBEESHQEKSIHXHGESLS

Expand: Super Highly Advanced Digitalized Bionic Electronic Exoskeleton Super Human Quality Exoskeleton Kit for Super High-Gravity Environments and Space Living