344
Productivity & Workflow355
Automation & Workflow224
Software Development251
Marketing & Growth192
AI Infrastructure & MLOps174
Writing & Content Creation203
Data & Analytics141
Photography & Imaging156
Design & Creative170
Customer Support131
Sales & Outreach125
Voice & Speech135
Education & Learning131
Operations & Admin87
ESPN showed an AI overlay during early 2026 World Series of Poker broadcasts that tracked player movements and guessed hand strength, drawing skepticism from pros.
In short: ESPN added an on-screen AI tool during early 2026 World Series of Poker broadcasts that tried to read players’ “tells”, and many poker pros questioned how useful it really is.
During ESPN’s early July broadcast of the 2026 World Series of Poker Main Event, viewers sometimes saw a new “AI tells detection” overlay. A “tell” is a small habit that might give away what a player is thinking, like how they breathe, move their eyes, or handle chips.
The overlay showed live measurements of a player’s movements and a chart that estimated what kind of hand they might have, such as a strong hand, a bluff, or a hand that needs a future card to improve. The tool was built by Luke Geel, an AI engineer for the US Air Force, and it was trained on video from the same tables used for the TV broadcast.
Poker pros interviewed by WIRED were skeptical, mainly because the AI may not have seen enough footage of the same people. The tournament had more than 9,000 entries, but only three tables were regularly recorded, so many players were barely on camera. Pro Michael Gagliano said even he struggled to learn much by rewatching every second of the streams.
Two-time WSOP Player of the Year Shaun Deeb also noted that many important tells are hard to capture on a TV feed. He said tells can include subtle signs like breathing changes or pulse, not just visible gestures (the famous “Oreo cookie tell” from the movie Rounders is a simplified example).
ESPN’s licensed production partner, Omaha Productions, told WIRED the tool would not be used for the final table, without explaining why.
This tool is aimed at viewers, but it raises a bigger question about how far AI should go in a game built on human judgment. Even if it is just TV graphics today, better versions could eventually be used to study opponents from hours of past footage, like a supercharged note-taker.
Source: Wired