AI Agents Tested as Fantasy Soccer Managers, With Mixed Early Results

A journalist let OpenAI's Codex manage a fantasy soccer team; the agent initially tried benching Erling Haaland but adjusted its picks over time, performing not yet better than humans.

Read the full story at Wired AI ↗

Timeline · 1 report

2026-10-28 18:30 · Wired AI
I Put a Bunch of AI Agents in Charge of a Fantasy Soccer Team. They’re Not Better Than Humans—Yet

More stories

OpenAI highlights immunologist using Codex to simulate single-cell drug responses — OpenAI (X)
OpenAI and ServiceNow expand partnership across enterprise workflows — OpenAI News
Merge CEO Shensi Ding discusses hands-on Codex use and AI fluency — OpenAI YouTube
Cognizant forms 25,000-strong OpenAI group days after Gemini push — The Next Web
Anthropic, OpenAI, Cloudflare and Google release AI agents that hunt security bugs in code — MarkTechPost
Legora builds agentic operating system for legal work using OpenAI models — OpenAI News
Google opens Android development tools to rival coding agents — The New Stack AI
Mistral releases weights for trillion-parameter 'Le Chonk' model — Mistral AI News

Get the daily brief of stories like this at 6:30 every morning →