Can artificial intelligence learn to read poker tells and figure out when someone is bluffing? AI engineer Luke Geel (geelai.net) created software designed to do just that, and his work was featured this year on the TV coverage of the World Series of Poker Main Event. I'm the author of some poker tells books (readingpokertells.com), and when I first heard about this program, I wondered: what exactly is his program doing? And how well does it work? In this episode, Luke explains how he built and structured his program. We discuss what his software can actually do, and why teaching machines to read behavior in poker is much harder than it might seem. Along the way, we explore some fascinating challenges of machine learning, including how AI finds patterns, why understanding an individual's psychology and circumstances matters, and how researchers can distinguish meaningful behavioral signals from noise. We also talk about Luke's newer work using AI to analyze sales conversations, with the goal of identifying subtle clues about people's intentions and discovering which communication strategies are most persuasive. This is a talk about poker, AI, psychology, and the possibilities and limitations of using machines to understand what people are thinking and feeling.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Can trying to read people's body language make investigators worse at finding the truth? Veteran interrogator and trainer Stan B. Walters, known as “the Lie Guy” (thelieguy.com) and author of “Principles of Kinesic Interview and Interrogation,” explains why he moved away from many of the nonverbal behavior ideas he once taught—and why he now focuses on listening to what people say. We discuss his and others’ research on telling lies from truth in real criminal interrogations, why bad ideas about nonverbal behavior and aggressive interviewing tactics persist in police training, and how investigators can accidentally feed suspects information that “contaminates” the interview and makes their job harder. Stan shares stories of an interview that unexpectedly uncovered a serial killer and a murder-attempt survivor whose important detail was missed because nobody asked the right questions. We explore what actually matters when listening to people: looking for gaps in people’s stories, thinking about how logical and verifiable their stories are, and more.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

How does someone make a living playing slot machines—and why would casinos let them? After joining professional gambler Chris Huang on a casino trip in Atlantic City, I talk with him about the unusual career of casino “advantage play” and how pro slot machine players capture the money left behind by other, less knowledgeable players. We explore why manufacturers create beatable machines, the psychological tricks that machine makers use to attract players, and the unethical actions some slot machine pros take to manipulate players into leaving profitable seats. Chris explains the risks pro slot machine players can encounter, how seemingly promising opportunities can turn into expensive mistakes, why a little knowledge can be dangerous, and what happens when you run out of cash in the middle of a long-term play. We also discuss online gambling “gurus” selling dubious claims of expertise, the secrecy and competition among slot professionals, and the appeal—and pressures—of making a living this way. Learn more about Chris at youtube.com/@gamblingeducationwithchris.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

A talk with Andrew Thompson, a New York City-area private investigator and a researcher of criminal behavior and interrogation techniques. Andrew shares how he gets people talking while lacking the authority and command of a police badge, and what studying FBI crime cases and interrogations taught him about linguistic clues to deception in people’s stories. We also discuss his research into criminal personality categories and how that may be tied to linguistic patterns. We discuss how mistaking signs of anxiety for guilt or deception can send investigators down very wrong paths; and how aggressive questioning can contribute to false confessions and other negative outcomes. We discuss why appearing uninterested in an important revelation from someone can sometimes encourage them to reveal more, and other tips on influencing and manipulating people in order to achieve investigative results. And Andrew discusses how AI advances have affected the investigative industry.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

On this podcast I sometimes explore the “behavior expert” industry. One thing I'm curious about is the value people say that they’ve received from “behavior expert” trainings and certifications. This is a talk with Gallia Winkler, a psychological coach and a behavioral student of Joe Navarro’s; she’s been certified in his Body Language Expert Program. I ask her about what drives her interest in nonverbal behavior, what value she believes she’s gotten from Navarro's teachings, and how those teachings have helped her in her personal and professional life.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

A talk with former CIA officer Kent Clizbe about the exaggerated, irresponsible claims made by many self-described “behavior experts,” focusing especially on Paul Ekman, Joe Navarro, microexpressions, and attempts to detect deception from body language. We discuss why facial expressions and physical movements cannot be interpreted through a universal dictionary, how cultural and individual differences make behavioral judgments especially difficult, and why nervousness or discomfort is rarely meaningful evidence of guilt or deception in high-stakes situations. We examine the failed TSA SPOT program, the influence of shows like “Lie to Me” (which was loosely based on Paul Ekman’s work), and the lack of convincing real-world, high-stakes examples supporting “behavior expert” claims. We also explore how behavioral hunches can contribute to tunnel vision, false confessions, and wrongful convictions; why games like poker can offer a more constrained and useful setting for behavioral reads; and why the most actionable information in high-stakes situations almost always comes from what people say, what they leave out, and how their statements compare with known facts.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

A talk with an Army Psychological Operations soldier about what military psy-op work really involves—and how different the reality is from many people's ideas about the nature of that work. We discuss his psy-op work in Afghanistan, why credibility and truth are usually much more persuasive and effective than deception, and fascinating historical operations involving surrender appeals, staged intelligence, and Vietnam’s eerie “ghost tapes.” We also explore the legal and ethical limits on influencing Americans, how social media has blurred those boundaries, how foreign influence campaigns exploit political polarization, and why “PSYOP” has become an all-purpose label for conspiracy theories. Finally, we examine the red flags that can help you identify self-proclaimed-but-deceptive military-persuasion experts (like Chase Hughes) who fabricate and exaggerate their credentials and experience to sell their psychology- and behavior-focused training and products.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Can machines spot a lie better than we can? I talk with psychology researcher Bennett Kleinberg, whose work brings together psychology, machine learning, natural-language processing, and deception detection. We explore why humans are bad at identifying lies, which verbal clues may reveal deception—and why nervousness is often misleading. Bennett explains how liars use detail and how level of detail can be a clue to deception, the fact that deception usually involves a good amount of truth in the mix and what that means, and what happens when human judgment is combined with AI. We also discuss the risks of the mysterious black-box nature of some machine learning systems, and how smarter, research-informed interviewing techniques could transform criminal investigations. For more details and a transcript, see this episode’s entry at www.behavior-podcast.com.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.