Codex Multi-Agent Team Improves Fantasy Football Picks, but Not Enough
In a WIRED experiment, Codex built a harness that coordinated agents reading news, analyzing match results, running prediction models and critiquing suggestions for an experimental Premier League fantasy team. The initial recommendations were notably poor, while specialized agents improved them; expanding the system beyond 100 agents produced little additional benefit and increased API costs, and the team remained below average.
The experiment offers a practical illustration of how task-specific multi-agent orchestration can improve AI forecasts without yet producing results that outperform skilled human prediction.
I have consulted my AI-powered crystal ball, and it’s telling me that frontier models are going to get a lot better at making predictions in the near future. Just ask my Premier League fantasy team.
A few weeks ago, I deployed a small horde of AI agents to craft and manage an experimental roster. 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.
I first looked at the potential for AI here a few years ago, playing around with a tool from the UK’s Turing Institute that selected teams after modeling previous fantasy league data. Its suggestions were remarkably bonkers—it didn’t incorporate real-world information, like a player’s injury or a team’s change in management.
This time, while on a flight to visit family, I asked Codex for help. First, I fed the model a couple of relevant research papers. Then, I asked it to build a harness—instructions and code that guides different agents through various steps—that would check recent news and run a model to make predictions.
#Codex#GPT-5#Grok 4#Claude Sonnet#Gemini#Llama#Prophet Arena#Prediction Arena#Metaculus Cup#ForecastBench