News for hackers. Stuff that matters.
Re:Markov chains are funnier than LLMs by trescenzi on Sunday August 18, 2024 @09:44PM (#41287094)
Reminds me of how the fake magic cards before chatgpt were always hilarious and sometimes playable, now they are usually playable and sometimes hilarious. Definitively a downgrade if you’d ask me.
Re:Markov chains are funnier than LLMs by JoshTriplett on Sunday August 18, 2024 @10:10PM (#41287188)
> always hilarious and sometimes playable

I saw plenty of those back then, and as far as I could tell, examples were always cherry-picked from a larger set.

Re:Markov chains are funnier than LLMs by stochaztic on Sunday August 18, 2024 @11:27PM (#41287544)
Yes, I ran the RoboRosewater account, which is where most people saw the concept I believe. I had a few documents with thousands of cards of output, went through them for any notable ones, and formatted and posted them. Probably 5-10% of the output made my personal cut for notability.
Re:Markov chains are funnier than LLMs by Applejinx on Monday August 19, 2024 @07:18AM (#41289983)
Then I salute you. Some of the funniest things I've EVER seen in my whole life was watching the LoadingReadyRun comedy troupe, doing their 'Desert Bus' fundraiser and punchy from lack of sleep, encounter RoboRosewater for the first time. It became a real tradition :)
Re:Markov chains are funnier than LLMs by kibibu on Sunday August 18, 2024 @11:12PM (#41287466)
Maybe the right solution is using a Markov chain or gpt1 to generate ideas and an LLM to cherry pick.