This is probably the only pro LLM post I will share, because I really want you to see how deep the rabbit hole goes. I do find it immensely hilarious that he has to use agents in order for the LLM to be relatively useful. So if you have to use agents to make your large language model productivity work for you, I think it fails on multiple levels, but I really want you guys to see how deep the Kool-Aid is and why we’re not getting over the hype even when the hype dies. My AI Skeptic Friends Are All Nuts https://fly.io/blog/youre-all-nuts/ #AI #LLM