Prediction error
The mismatch between expected and actual sensory input; one theory holds that minimizing this error is the brain's fundamental motivation.
As defined in Paul Bloom on Psych, Psychology, and the Human Mind
Other definitions
The difference between what an AI model predicted and what actually occurred; in VOE testing, elevated prediction error indicates 'surprise' and suggests the AI violated its expected understanding of physics
LeWorldModel: Stable End-to-End JEPA World Models From Pixels
Where it comes up · 11
- 235 | Andy Clark on the Extended and Predictive Mind12 claims
- 322 - Predicting Reality7 claims
- Charan Ranganath4 claims
- LeWorldModel: Stable End-to-End JEPA World Models From Pixels3 claims
- 247 - Constructing Minds3 claims
- 113 - Consciousness And The Self2 claims
- 320 - Constructing Self And World2 claims
- 264 - Consciousness And Self Rebroadcast2 claims
and 3 more
Most important claims · 10 of 38Search all claims for “Prediction error” →
- The historical problem with training world models through prediction is 'representation collapse'—where an AI can achieve perfect prediction accuracy by mapping all inputs to the same blank representation (e.g., zero) without learning any actual physics, because the loss function only penalizes prediction error, not learning quality.LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- Often the correct move for a prediction-driven system is to temporarily increase its own uncertainty so as to better minimize prediction errors over the long run, which gives surprise its value; we artificially curate environments to surprise ourselves, and art and science may largely be the curation of environments that harvest surprises improving our generative models.235 | Andy Clark on the Extended and Predictive Mind
- When viewing the concave side of a hollow face mask, people see the nose facing outward because the brain has such a strong learned prediction that noses stick out that it overrides the perfectly good sensory information specifying concavity, producing a false but compelling convex-face experience.322 - Predicting Reality
- Neurologically, we hold internal predictive models of our perceptual and behavioral states; when stimuli conform to predictions their salience is inhibited and they fade, while prediction errors—surprises—are what we notice, and this applies to both positive and negative stimuli.359 - Getting Used To It
- Stage magic works by carefully controlling attention, which the predictive brain allocates to where it expects good information; because dramatic events can occur where attention is not directed, magicians can make things appear or disappear unnoticed, demonstrating attention as a moment-by-moment balancing act in the predictive system.235 | Andy Clark on the Extended and Predictive Mind
- Researchers tested LayWM's physics understanding using a violation-of-expectation (VOE) test analogous to how human psychologists test infant understanding of object permanence—by measuring prediction error when the AI encounters physical impossibilities versus expected violations like color changes.LeWorldModel: Stable End-to-End JEPA World Models From Pixels
- There is no single principle of human motivation; a pluralist view is correct. The reason you eat when hungry differs from why you became a college president or why you scratch an itch, and attempts to reduce all motivation to one principle become banal tautologies ('people do what they do').Paul Bloom on Psych, Psychology, and the Human Mind
- The predictive architecture makes us susceptible to illusions where strong predictions trump real sensory evidence, as in the hollow mask illusion where a concave mask is seen as a normal outward-facing face; people on the autism spectrum are slightly less susceptible to this and the McGurk illusion, probably because sensory inputs are enhanced relative to expectations.235 | Andy Clark on the Extended and Predictive Mind
- The canonical computation of the brain is attempting to predict the current flow of sensory information; at the basic time scale it is predicting the present, acting as a guessing machine that combines prior experience with current sensory evidence to estimate the true state of the world, which lets us use the past to make better sense of present sensory signals.235 | Andy Clark on the Extended and Predictive Mind
- The brain constructs perception by issuing top-down predictions (from a generative model) about likely sensory stimulations and using them to clean up, discard, and amplify incoming signal; sensory information is swapped for prediction error early in processing, so everything we see, touch, and feel is framed by these predictions rather than read directly off the world.322 - Predicting Reality