Every breath you fake

·25 min·2 clips

Can a machine look at your face and know what's going on inside your head, and could it be better at it than we are?

The question sounds simple at first. Can a machine look at a face and know what is happening inside someone's head better than another person can? Click Here gives that idea room to breathe. Karen Duffin starts with the way people read bodies, brows, and half-smiles every day, then turns to the technology trying to copy pieces of that habit. The promise has an easy pull. Computer vision can measure tiny facial movements that people may miss. Then the story gets less tidy. Ekman's system breaks emotions into combinations of action units, but that framework only goes so far. Once AI systems learn from the internet, they take in a data world full of contradiction, performance, and deception. Cleaner data would not fix the deeper problem. A system may detect nervousness, but it cannot know whether someone is lying or scared of being doubted. That is where the episode lands its point. Recognizing an emotional signal is different from knowing what caused it in that moment. Context does the hard work. Without knowing what happened five seconds earlier, software can put a normal reaction in the wrong box. The airport example makes it easy to feel the risk. A missed pickup, a long customs line, and visible frustration could be read as aggression by a scanning system. The result is not abstract. Someone could be pulled aside because software saw an emotion, lost the story around it, and treated uncertainty as danger. These tools are also moving into health care and HR, including systems meant to analyze responses from people with dementia or Alzheimer's. The episode does not flatten the issue into rejection. It asks whether detection without context is sturdy enough for decisions that matter.

As heard by us

A clear, uneasy look at emotion AI and the danger of mistaking facial signals for human context.

Click Here treats emotion AI less as a gadget story than as a problem of interpretation. Karen Duffin builds the episode around an everyday human habit, reading faces and body language, then follows what happens when computer vision systems try to do the same thing at scale. Dr.

Read the full review in PlayNext →

Why you'd press play

AI might already be reading your face better than the person standing next to you.

Read the full recommendation in PlayNext →

Listen to the show on

Apple Podcasts Spotify

Play clips from this episode More from Click Here