As shown in Jaderberg et al. (2019), multiagent reinforcement learning is a promising avenue for artificial intelligence research, as agents have been documented to collaborate at human-level performance in the three-dimensional multiplayer game Quake III Arena in Capture the Flag mode. While it is impressive that multiagent collaboration at human-level performance is now possible, it also raises the inevitable question if we, as human-beings, have the skill and will to collaborate with AI agents in the future? As the findings arguably allude to, a failure to do so could erode our historical competitive advantage of collaboration in the race against the machines. Consequently, we need to find our appropriate coopetition strategy, i.e. The optimal combination of collaboration and competition, if we are to co-exist with AI agents in the future. Or to paraphrase the famous Danish scientist and artist Piet Hein: It is a question of “co-existence or no existence”.