ESPN Is Bringing Back the World Series of Poker, This Time with AI That Spots Players Bluffing

AI is learning to spot poker bluffs by watching the tiny tells players try to hide.

08 Jul 2026, 17:52 by Tibi Puiu · ZME Science

Credit: Grace Hughes, Luke Geel, Sportico.

The poker face may be running out of places to hide.

As the World Series of Poker returns to ESPN for the first time since 2021, the broadcast will include a new kind of spectator: an artificial intelligence system trained to look for subtle clues in the human body.

The tool, developed by independent AI engineer Luke Geel and enlisted by Peyton Manning’s Omaha Productions, analyzes past results and player behavior, including posture and blink rate, to identify moments when someone may be bluffing or holding the “nuts,” poker slang for the best possible hand.

For now, Omaha plans to use the system cautiously. The AI-assisted broadcast will focus on players only after they have been eliminated, avoiding real-time exposure that could affect the game.

“We’re trying to bring back some of what was great about the World Series during the [Chris] Moneymaker boom and some of what’s been great about poker in the last 5-to-10 years,” Omaha head of content Dan Gati told Sportico.

“A lot of people think that because poker is not on mainstream television that it’s not doing as well. Live poker is as robust as it’s ever been. And I think the next step is bringing it back to ESPN for the mainstream to see it again.”

The Old Game Meets a New Viewer

Poker has always rewarded players who can read what others try to conceal. This is why live poker is an entirely different beast from playing online. Players study bet sizes, timing, posture, speech and the slightest hesitation. The best players also work hard to erase those signals. You’ll often see professional poker players wearing sunglasses at tournaments for this exact reason.

Geel’s AI system tries to do what sharp poker players and some commentators already do, but more systematically. It scans video for repeated physical patterns — a blink, a shift in posture, a change in stillness — and compares them with what happened in previous hands.

Get smarter every day...

Stay ahead with ZME Science and subscribe.

Daily Newsletter
The science you need to know, every weekday.

Weekly Newsletter
A week in science, all in one place. Sends every Sunday.
No spam, ever. Unsubscribe anytime. Review our Privacy Policy.

Thank you! One more thing...

Please check your inbox and confirm your subscription.

But building it, Geel said, was not as simple as feeding the system old footage.

AI Is Rewriting the Rules of Retirement Savings
Google’s AlphaProof Can Work on Mathematical Proofs Once Thought Beyond Machines
Scientists brew the future with AI that ‘tastes’ Belgian beer to make it better
Researchers create smartphone app that can diagnose depression from facial features

“It was significantly more difficult than I had initially hoped,” he said. “I can’t just, like, upload a YouTube URL and say, ‘find their tells.’”

In fact, Geel is skeptical his system can work at all on the most elite players. At least for now.

“Some people have asked, like, ‘Hey, why don’t you run this on a top professional poker player, like Daniel Negreanu?’” Geel told Sportico. “He’s not going to have any tells. He’s probably worked hard to remove them. I just don’t see any reason to do that yet. Maybe in the future, when AI becomes even better.”

Poker AI has already transformed the game, but mostly from the inside. Systems such as Libratus and DeepStack showed years ago that machines could beat professionals in heads-up no-limit Texas hold’em, a game built around hidden information, incomplete knowledge and bluffing. This new broadcast tool does something different. Rather than trying to compete people, it watches them.

Beyond Poker

The same idea is spreading through sport and business: use cameras to detect intent before action becomes obvious.

In soccer, researchers have built AI models that analyze a penalty taker’s movement before the kick. David Freire-Obregón, an associate professor in Spain who has studied the problem, says that future systems may help goalkeepers spot patterns in a player’s run-up and learn individual habits.

But even there, prediction has limits.

“That said, I don’t think AI will ever make penalty shootouts predictable,” Freire-Obregón said.

The same may hold for poker. Once players know machines can spot certain habits, they may train themselves to hide those habits, or deliberately fake them. Surveillance changes behavior. In games of deception, the watched person adapts.

That is why the WSOP experiment feels larger than a television gimmick. With better cameras and more data, Geel said future systems could track signals such as heart rate or facial flushness. Similar tools could interest car dealers studying what excites shoppers, or coaches trying to identify an athlete’s tendencies.

For now, poker fans will see the technology as part of the show, not part of the contest. The $10,000 buy-in Main Event began on the ESPN app, with final table coverage scheduled for ESPN in early August.