NEWS · MODELS · #2746
Author deploys Codex-built AI agents to manage Premier League fantasy team; not yet outperforming humans
The author built a harness with OpenAI Codex that coordinates dozens of AI agents (news readers, modelers, critics) to select and manage a Premier League fantasy soccer team; despite improved capabilities versus years ago, the system has not yet outscored the human average. The article cites research by Haifeng Xu and others showing frontier models (reported ranking: GPT-5, Grok 4, Claude Sonnet, Gemini, Llama) improving at prediction tasks and benchmarks like Prophet Arena, while other experiments such as Prediction Arena and ForecastBench show mixed returns and evidence of models improving over time.
KEY POINTS
- The author built a harness with OpenAI Codex that coordinates dozens of AI agents (news readers, modelers, critics) to select and manage a Premier League fantasy soccer team; despite improved capabilities versus years ago, the system has not yet outscored the human average.
- The article cites research by Haifeng Xu and others showing frontier models (reported ranking: GPT-5, Grok 4, Claude Sonnet, Gemini, Llama) improving at prediction tasks and benchmarks like Prophet Arena, while other experiments such as Prediction Arena and ForecastBench show mixed returns and evidence of models improving over time.
- This illustrates that while modern models and agent orchestration can aggregate far more information than before, they still lag top human forecasters in many real-world prediction tasks — a dynamic that could reshape trading and forecasting roles as models improve.
WHY IT MATTERS
This illustrates that while modern models and agent orchestration can aggregate far more information than before, they still lag top human forecasters in many real-world prediction tasks — a dynamic that could reshape trading and forecasting roles as models improve.