[DubiousPusher]

I guess I'm very confused as to why just throwing an LLM at a problem like this is interesting. I can see how the LLM is great at decomposing user requests into commands. I had great success with this on a personal assistant project I helped prototype. The LLM did a great job of understanding user intent and even extracting parameters regarding the requested task.

But it seems pretty obvious to me that after decomposition and parameterization, coordination of a complex task would much better be handled by a classical AI algorithm like a planner. After all, even humans don't put into words every individual action which makes up a complex task. We do this more while first learning a task but if we had to do it for everything, we'd go insane.

[tsimionescu]

There are many hopes, and even claims, that LLMs could be AGI with just a little bit of extra intelligence. There are also many claims that they have both a model of the real world, and a system for rational logic and planning. It's useful to test the current status quo in such a simplistic and fixed real-world task.

[DubiousPusher]

There's the rub I suppose. I don't think an LLM can achieve AGI on its own. But I bet it could with the help of a Turing machine.