It’s wild how Gemini is leading the pack on model capabilities—context length, fine-tuning, multimodality—and yet using it feels like you’re solving a UX puzzle just to ship a basic feature. It’s almost ironic: Google builds some of the smartest models out there, but makes devs feel dumb trying to integrate them. Imagine the adoption surge if the experience was even half as smooth as OpenAI’s. Power without usability is just potential, not progress.