Osmantic founder @TheAhmadOsman warns companies relying on cloud AI are building on models that can be changed, slowed down, or taken away without them even knowing: "If you're using any quantity of tokens, you should start hosting your own LLMs. You don't know when a model is gonna change on you. APIs are always having this latest endpoint, so you always end up, it gets rug pulled from underneath you" "How could you tell if a certain country is getting 5, 10 IQ points drop in their inference…