Researchers use brain signals to distinguish and correct AI errors in simulations

Researchers at KAIST and Microsoft Research Asia demonstrated a system that uses brain signals to distinguish whether an AI has misunderstood a person's goal or chosen an unexpected method. Their Neural Value Alignment technique feeds those distinctions into an algorithm that can adjust its actions in real time. The system uses electroencephalography, which measures electrical activity through electrodes, and deep learning to classify different responses to AI behavior. Experiments produced distinct patterns for goal errors, method errors and both together. The demonstration used simulations rather than a freely operating robot. Noisy signals and the need for electrodes leave reliability during natural interactions unresolved.