> I even tried Django, thinking I'd stick with Python, but it's accumulated so much over the years. Too much magic, too much stuff.
Heh. The problem with Django is certainly not that it has accumulated too much.
Anyway, this seems a bit silly. There's nothing here that is "agentic", and javascript is certainly not a language that is especially suited for LLMs except that the training data is there, but that's even more true of React or Django.
Yes, the main thing is that we're trying to see if AI can have an easier time using one framework vs. another, and how important it is.
All Rails-like frameworks (Django, Laravel, or Wasp in this case) claim its helpful to use something opinionated and structured, which makes sense (the tradeoff is the flexibility, of course).
We've run some early tests[1] but plan to do a more substantial benchmark next.
Heh. The problem with Django is certainly not that it has accumulated too much.
Anyway, this seems a bit silly. There's nothing here that is "agentic", and javascript is certainly not a language that is especially suited for LLMs except that the training data is there, but that's even more true of React or Django.