▲ 203 ▼ ChatGPT gets code questions wrong 52% of the time (www.theregister.com) submitted 3 years ago by yogthos@lemmy.ml to c/technology@lemmy.ml 66 comments fedilink hide all child comments
[–] buh@hexbear.net 36 points 3 years ago (3 children) Every time I’ve used it to generate code, it invents frameworks that don’t exist permalink fedilink source hideshow 6 child comments replies: [–] just_browsing@reddthat.com 32 points 3 years ago (1 child) CTO material right there. permalink fedilink source parent hideshow 2 child comments replies: [–] aaaaaaadjsf@hexbear.net 6 points 3 years ago Lmaooo permalink fedilink source parent [–] maynarkh@feddit.nl 15 points 3 years ago Just like an average enterprise architect. permalink fedilink source parent [–] CriticalResist8@hexbear.net 6 points 3 years ago I've had some success with it if I'm giving it small tasks and describe in as much detail as possible. By design (from what I gather) it can only work on stuff it was able to use in training, which means the language needs to be documented extensively for it to work. Stuff like Wordpress or MediaWiki code it does generally good at, actually helped me make the modules and templates I needed on mediawiki, but for both of those there's like a decade of forum posts, documentation, papers and other material that it could train with. Fun fact: in one specific problem (using a mediawiki template to display a different message whether you are logged in or not), it systematically gives me the same answer no matter how I ask. It's only after enough probing that GPT tells me because of cache issues, this is not possible lol. I figure someone must have asked about this same template somewhere and it's the only thing it can work off of from its training set to answer that question. I also always double-check the code it gives me for any error or things that don't exist. permalink fedilink source parent
[–] just_browsing@reddthat.com 32 points 3 years ago (1 child) CTO material right there. permalink fedilink source parent hideshow 2 child comments replies: [–] aaaaaaadjsf@hexbear.net 6 points 3 years ago Lmaooo permalink fedilink source parent
[–] maynarkh@feddit.nl 15 points 3 years ago Just like an average enterprise architect. permalink fedilink source parent
[–] CriticalResist8@hexbear.net 6 points 3 years ago I've had some success with it if I'm giving it small tasks and describe in as much detail as possible. By design (from what I gather) it can only work on stuff it was able to use in training, which means the language needs to be documented extensively for it to work. Stuff like Wordpress or MediaWiki code it does generally good at, actually helped me make the modules and templates I needed on mediawiki, but for both of those there's like a decade of forum posts, documentation, papers and other material that it could train with. Fun fact: in one specific problem (using a mediawiki template to display a different message whether you are logged in or not), it systematically gives me the same answer no matter how I ask. It's only after enough probing that GPT tells me because of cache issues, this is not possible lol. I figure someone must have asked about this same template somewhere and it's the only thing it can work off of from its training set to answer that question. I also always double-check the code it gives me for any error or things that don't exist. permalink fedilink source parent