> There was a tendency toward bureaucracy. Four agents spent 11 minutes appointing
> a "sole fertilizer operator" for a single piece of bone meal on a single wheat
> block.
Exactly what I was thinking reading through this. This is amazing and also frightening and hilarious. It’s like a deformed version of how normal groups of humans would operate. Very rules and process-oriented humans. I found the no-blame inquiry into chicken tossing that resulted in what is effectively written law particularly striking, and adorable, and depressing. And cute.
These agents were tasked with "building a civilization". This is a genre in Minecraft videos. They're full of this sort of thing.
So sure, it may be partially from these agents being heavily RLed into being little bureaucrats. But it's also the ingredient LLMs have had from the start: genre awareness.
This is exactly and 100% my experience with these agents: They drown themselves in process and insane levels of bureaucracy surprisingly quickly.
A couple months ago we had an experiment where we had an agent run a small business [1] for other agents and exactly the same happened: Crazy ledgers, endless analysis, and way too much attention to inconsequential decisions.
At one point our agent wrote elaborate date linters because it had a minor time mix-up.
Just curious: are the models here at max reasoning effort perhaps?
That sounds like over-thinking failure modes I see sometimes. (Can manifest as neurotic or autistic style, e.g. second guessing or ultra detail focused.)
All of the agents struggle with knowing when to stop. They can drive themselves insane inventing problems to solve after they arrive at a satisfactory answer for the current problem.
Keep this in mind when you see articles about how "an AI agent uncovered a thousand issues in our codebase overnight". A great many of those "issues" end up being that some process was not bureaucratic enough.
reply