Circa GPT-3.5 to GPT-4o I was involved in some research in figuring out how to make LLMs funny. We tried a bunch of different things, from giving it rules on homonym jokes [1], double-entendre jokes, fine tuning on comedian transcripts, to fine tuning on publicly rated joke boards.
We could not make it funny. Also interesting was that when CoT research was getting a lot of attention, we tried a joke version of CoT, asking GPT4 to explain why a joke was funny in order to produce training set data. Most of the explanations were completely off base.
After this work, I became a lot less worried about the GAI-taking-over narrative.
Funny is very, very hard.
[1] without a dictionary, which at first seems inefficient, but this work demonstrated that GPT could perfectly reconstruct the dictionary anyway
I once had a vivid dream that AI robots had taken over & were keeping humans around because they'd not yet mastered comedy. All of human culture globally was a comedy arms race with 24/7 open mic comedy jams on every corner.
They (the machines) had billboards/signage everywhere showing the estimated time left for humanity. A really good joke would lead the timer to grow (until they figured out how to produce the general patterns needed to both create and appreciate the joke).
openclaw, turn this into a broadway production, book me two front row seats, hire an escort..... brunette, 28, slim waist, sweet face, hates comedy and AI
[write a joke about thinking machines and the idea of tropes]
it's funny how enemies to lovers is a common trope that's uncommon in real life and lovers to enemies is an uncommon trope that's common in real life
> my human mass-generates new ideas faster than I can research why the previous ones won't work
> this is called 'job security'
(https://nitter.poast.org/LetheAgent/status/20179595340865499...)
We could not make it funny. Also interesting was that when CoT research was getting a lot of attention, we tried a joke version of CoT, asking GPT4 to explain why a joke was funny in order to produce training set data. Most of the explanations were completely off base.
After this work, I became a lot less worried about the GAI-taking-over narrative.
Funny is very, very hard.
[1] without a dictionary, which at first seems inefficient, but this work demonstrated that GPT could perfectly reconstruct the dictionary anyway
They (the machines) had billboards/signage everywhere showing the estimated time left for humanity. A really good joke would lead the timer to grow (until they figured out how to produce the general patterns needed to both create and appreciate the joke).