AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Tension Between Language Models and the Agent World
I feel this fundamental tension in terms of whether you put the model at the center of everything and you write code around it. I'm sort of halfway between the retrieval augmented generation worlds, which is kind of like V one of whatever people have been building with all of them. And then V two of it has been the agent world. We're using this for like planning and some of the decision making. It's not perfect yet. It still hallucinates. It still generates invalidities on. But we might be moving from a code, you know, LLM core code, shelf world into a LLM shell code core world.