I hear you, though I’m less focused on the choice of UI libraries and more on how little control we have over how prompts are routed internally.
Sometimes I want a model that reasons deeply, other times I want one that is more creative. Right now, it feels like gpt-5 forces everything through the same pipeline, even when a different mode would be better suited to the task.
For web app generation, gpt-5 seems to route my prompt to the reasoning model. Interestingly, gpt-4.1 often produced more creative or aesthetically interesting designs. In some cases, a bit of controlled hallucination (via temperature) is actually desirable, especially when generating UI ideas. Anyone else seeing this tradeoff?
Sometimes I want a model that reasons deeply, other times I want one that is more creative. Right now, it feels like gpt-5 forces everything through the same pipeline, even when a different mode would be better suited to the task.