Re:Next-generation AI models
by nevster on Wednesday June 22, 2022 @12:29AM
(#31832023)
Seconded. Tabnine's suggestions were way worse than IntelliJ's suggestions. It was very annoying. Uninstalled it after a giving it a good try.
[ Parent
| on HN ]
Java was the one language where I found TabNine to fall short. I think it’s a harder case for AI completions, because the existing story for editing Java is a lot less like editing text than other languages.
I haven’t tried Copilot for editing Java, because I’m no longer working in any Java code bases, but I wonder if it does a better job.
I uninstalled T9 for this reason: bad suggestions superseding the regular autocomplete, this is just not good.
I have yet to compare to copilot.
Re:Next-generation AI models
by bluelightning2k on Wednesday June 22, 2022 @05:52AM
(#31833830)
Same issue with the autocompletes pushing the ground-truth out.
I actually installed a third-party extension which implements their autocomplete differently.
So weird that they didn't hear such major/consistent feedback. (Maybe they didn't want to tank their 'suggestions taken' number?)
Re:Next-generation AI models
by BrandonJung on Wednesday June 22, 2022 @07:36AM
(#31834659)
please take a look at inline suggestions that will be in grey and not in the regular autocomplete box. It is now the default setup.
Re:Next-generation AI models
by MattPalmer1086 on Wednesday June 22, 2022 @04:46AM
(#31833464)
Same here. I gave it a go for a while, thinking I must be holding it wrong or something.