News for hackers. Stuff that matters.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by hirvi74 on Thursday November 19, 2026 @09:29PM (#50569433)
> I've done exact head-to-head comparisons of OpenAI models and Opus 5.5, and Opus is so much better

I am just curious if you have always noticed this trend? I swear, a year ago or so, I was having the complete opposite experience, but something changed in the 3-6 months. I cannot comment on Swift UI, but Swift experiences have been the nearly identical. I felt like GPT used to be so much better with Swift (and C#) than Opus.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by WaltPurvis on Thursday November 19, 2026 @09:52PM (#50569574)
I can't speak to the historical trend because I've only been doing substantial SwiftUI work with these models for about three months. But in my head-to-head comparisons, it's not strictly code where Opus has been better. Codex has made some very questionable choices in app architecture, etc., which I don't see from Opus.