Check out how quickly these AI agents learn, get better and figure out how to use tools use while playing a simple game of hide-and-seek (3 min video) It’s amazing…

• Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported.
• The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day produce extremely complex and intelligent behavior.

Learn more: https://openai.com/blog/emergent-tool-use/