I Put a Bunch of AI Agents in Charge of a Fantasy Soccer Team. They’re Not Better Than Humans—Yet
WIRED · 29 Oct 2026, 04:30 AEST
An experiment with AI agents managing a fantasy soccer team shows they are not yet better than humans. The AI initially made poor decisions but adapted over time.
Key facts
- To experiment with AI’s predictive skills, I let Codex loose on a fantasy team.
- It tried to bench Erling Haaland at first, but it soon learned the error of its ways.
- Given the proliferation of AI agents into pretty much every aspect of our lives, I wanted to know if a swarm of bots could put together a winning team.
- This time, while on a flight to visit family, I asked Codex for help.
Read aloud
An experiment with A I agents managing a fantasy soccer team shows they are not yet better than humans. The A I initially made poor decisions but adapted over time. To experiment with A I’s predictive skills, I let Codex loose on a fantasy team. It tried to bench Erling Haaland at first, but it soon learned the error of its ways. Given the proliferation of A I agents into pretty much every aspect of our lives, I wanted to know if a swarm of bots could put together a winning team. This time, while on a flight to visit family, I asked Codex for help.
Sources in this cluster
- I Put a Bunch of AI Agents in Charge of a Fantasy Soccer Team. They’re Not Better Than Humans—Yet
WIRED · 29 Oct 2026, 04:30 AEST