Re:Terence Tao, "Machine Assisted Proof" [video]
by kaba0 on Thursday February 15, 2024 @03:52AM
(#39380476)
> Leonardo Da Vinci and Einstein
Then it would be able to logically reason, which it absolutely can’t do.
It’s a next generation search engine, which is very good at language-related tasks (and translating a python code it has in its training set to your language is a language task, that’s why it can be applicable to certain programming tasks).
Re:Terence Tao, "Machine Assisted Proof" [video]
by zozbot234 on Thursday February 15, 2024 @05:23AM
(#39381030)
It can say "let's think this through step by step", which is good enough for most cases.
Re:Terence Tao, "Machine Assisted Proof" [video]
by thatguysaguy on Thursday February 15, 2024 @04:10AM
(#39380587)
I posted a few example questions (which are definitely way below Einstein level) in another comment. It's not doing too well! Do you have any links to conversations where it was particularly helpful? I do wonder if my GPT usage is bad in the same way my parents' Google usage is.
Re:Terence Tao, "Machine Assisted Proof" [video]
by kjqgqkejbfefn on Thursday February 15, 2024 @11:36AM
(#39384821)
Maybe try asking your questions on phind.com. It does RAG on top of GPT4 so it might be able to base its answers on the paper or github issue you mentioned.
Re:Terence Tao, "Machine Assisted Proof" [video]
by throwaway920102 on Friday February 16, 2024 @10:40PM
(#39406139)
Well, Einstein and Da Vinci were fallible as well.
Now imagine they have zero problem with you interrupting them to ask the stupidest question or the most profound, difficult question, as long as you want, and if you don't like their answer you can tell them to try again. And they don't care how often you do either.
What kinds of questions might you ask that coworker in the course of your work? It's highly individual.