zlacker

>>blueri+(OP)
I personally feel like some of the AI hype is driven by it's ability to create flashy demos which become dead end projects.

It's so easy to spin up an example "write me a sample chat app" or whatever and be amazed how quickly and fully it realizes this idea, but it does kinda beg the question, now what?

I think in the same way that image generation is akin to clipart (wildly useful, but lacking in depth and meaning) the AI code generation projects are akin to webpage templates. They can help get you started, and take you further than you could on your own, but ultimately you have to decide "now what" after you take that first (AI) step.

>>ddxv+zf
The demos I see all make compromises in order to work that hobble you from hardening them or otherwise lock you to very specific conceptualizations that you simply wouldn't have building from the smallest low level building blocks or even starting at a super high level state machine placeholder. In my experience no matter how hard I try it will be guided by the weights of the total generated output towards something that doesn't understand the value of compartmentalization, and will add tokens that make its probabilities work internally above all.