Re:Google dusts off the failed Google+ playbook to fight Cha...
by mchaver on Friday March 10, 2023 @03:11AM
(#35091822)
> How do you verify if what ChatGPT returns is actually correct?
A bit ironically, if it is regarding a fact, I perform a search on DDG or google and find an authoritative website or paper to corroborate it. So it still feels like search outside of an LLM is an important tool. If the result is code I can test it myself.
Re:Google dusts off the failed Google+ playbook to fight Cha...
by IanCal on Friday March 10, 2023 @03:42AM
(#35092064)
There needs to be some lexicon for this kind of thing. Theres a parallel with NP problems, some things are hard to figure out but easy to verify. Others hard to do both.
A bit ironically, if it is regarding a fact, I perform a search on DDG or google and find an authoritative website or paper to corroborate it. So it still feels like search outside of an LLM is an important tool. If the result is code I can test it myself.