Re:Ask HN: Is the world ready for the inevitable ChatGPT rug...
by rabbits_2002 on Wednesday August 16, 2023 @02:16PM
(#37151304)
so I am not crazy, 3.5 seems much dumber than before. It used to be able to solve coding problems and have a 75% working solution, now it spits out literal nonsense or doesnt even try.
[ Parent
| on HN ]
Re:Ask HN: Is the world ready for the inevitable ChatGPT rug...
by runjake on Wednesday August 16, 2023 @07:36PM
(#37155311)
While I agree that 3.5 seems to be getting worse, I haven’t had it spit out “literal nonsense”. It’s still pretty decent as spitting out code for me.
What’s an example prompt that will induce nonsense?