alt Hacker NewsI’ve had great luck building SwiftUI apps with GPT-5.5 (now GPT-5.6 Sol), Opus 4.8 and Fable 5. I’m just offering another data point, not suggesting on the effectiveness of DSLs for this.
One line of thinking can be that frontier models are already powerful enough to brute force through it, but this might be a stronger indicator for success for smaller models.
No argument that it works, it definitely does. I just think the LLMs have a hard time with tweaks/modifications of any kind, more so than what I see even in a custom GUI toolkit I’ve built that it has zero training data on.
Asking for simple changes to SwiftUI interfaces I’ve one-shot is always a frustrating experience for me