Hah. We're doing AI, but we're doing vision-based stuff and not LLMs. For us, the problem has been deploying models.
Google and AWS helpfully offered their managed LLM AI services, but they don't really have anything terribly more useful than just machines with GPUs. Which are expensive.
Google and AWS helpfully offered their managed LLM AI services, but they don't really have anything terribly more useful than just machines with GPUs. Which are expensive.
I'm going to check fly.io...