| It is likely we can do better than 1:1 human input to GPT output on current tech; but the human in the loop is doing a lot of work very easily that the LLM is very bad at, just like the LLM is doing a lot of work very easily that is otherwise laborious for the human. We can't just take the things that the LLM is bad at and humans do easily and expect to fix it with more LLM. Right now we have: Step 1: Human reasoning, tool use, input. Step 2: LLM output. Step 3: Human reasoning, tool use, input. Step 4: LLM output. &etc. The observation that the input and output are both just text makes it possible to make "agents". But the "agent" movement trying to totally close the whole loop right away is way too early. It's fine to lay the groundwork though, and the frameworks for it, like AutoGPT, can be used to just do a couple extra steps rather than close the whole loop. Plugins and browsing can be seen as merging some of step 2 and 3. But then you still need the &etc iteration with the human closely in the loop. Chain of thought prompting techniques are similarly an attempt to merge a little bit of the human's process of vetting the output by trying to get better output in individual iterations. Sometimes I make the LLM output multiple options and pick the best one with its reasoning; this is really just compressing multiple runs of the LLM and having it pick one, rather than me retrying if I get a bad output. Anyway I think this is the right way to look at it; these are good tools for trying to compress iterations of human-in-the-loop. For some things maybe we'll eventually remove the human, but we shouldn't expect it right now. The twitter demonstrations of "it did the whole thing" are a trick; good for influences, but not realistic right now. |