Re:GPT-3 fails horribly, then I coax it into figuring out ho...
by IIAOPSW on Sunday July 10, 2022 @03:09AM
(#32042513)
The way it seems to be mathematically illiterate and just kind of badly faking it to get through a conversation feels distinctly like a real conversation with some people.
[ Parent
| on HN ]
Re:GPT-3 fails horribly, then I coax it into figuring out ho...
by PlasmonOwl on Sunday July 10, 2022 @07:10AM
(#32043629)
It's fascinating. Some more critical observers are very disappointed with performance like this. I've seen comments about how dumb it seems. I don't think it does, I think you are bang on. It seems somewhat like a conversation with a child.