Finally joined the other app that shall not be named. Will be mirror posting here/there so my YT links don't sink to the bottom of the abyss.
bsky.app/profile/emerge…
official paper for mindcraft!!!
This paper introduces the mindcraft framework and provides some benchmarks for multi-agent LLM collaboration in minecraft. Really cool stuff, very glad to have been able to help out making pretty videos. Check it out!
The real world is an embodied multi-agent system with natural language communication. What if we had a benchmark and platform to study those challenges?
⛏️Introducing MINDcraft and MineCollab, the 1st platform and benchmark for studying embodied multi-agent LLM collaboration!
Playing with open-ended AI Agent behavior.
Here's an AI Agent (claude code) making a self-portrait.
It "evolves" the image by: writing code that generates image -> view image -> modify image -> view -> modify -> repeat.
I realized the LLM agents can simulate Conway's Game of Life in Minecraft. This was always possible, but very tricky to do. This is claude-thinking.
I wonder what else was always possible.
claude 3.7 villager utopia skyscraper
Not noticeably better at building than 3.6.
Definitely more confused, gets formatting/syntax wrong a lot, similar problem for every reasoning model I've used in minecraft. I suspect they are overfitting on benchmarks, and struggle to
Mindcraft now has an official research paper behind it! We focused on the collaboration AI agents in minecraft, and introduce mindcraft as a framework for future research. I made a video to showcase it! Thanks to coauthors @kolbytn@isadorcw@rajammanabrolu@Lianhuiq
Paper,
Introducing The Darwin Gödel Machine: AI that improves itself by rewriting its own code
sakana.ai/dgm
The Darwin Gödel Machine (DGM) is a self-improving agent that can modify its own code. Inspired by evolution, we maintain an expanding lineage of agent variants,