[dinkumthinkum]

I am somewhat shocked by the level of incredulity people are having in this thread toward having an alternative to traditional APIs for use with LLMs. It is a lot of the same "If the AI is incapable of <blah blah> then why would anyone use it?". I guess I don't see what the big deal is in having a more robust standard for interfacing with a system such as LLMs. Do they fear the engineering effort is orders of magnitude? I mean really, I think it is more of an anti-AI or anti-LLM sort of sentiment, which, frankly, I am quite sympathetic to, but this is sort a bad argument or position to have.