In preparing a “futuristic” talk about Physiological Computing, I’m pondering how a system might adapt itself to physiological data indicating that the user just got upset or bored or exasperated.  In the past, I’ve focused on the Gilleade et al (2005) classification where the system may help the user, challenge the user or emote the user.  In my view, whether these adaptations are overt or covert, what the system is attempting to do is manipulate the state of the user in a desired direction (generally to preserve task engagement and minimise those states that may disrupt engagement).  On the other hand, the system could simply mirror the psychological state of the user.  This mirroring approach comes in two categories.  First of all, to mimick the state of the user in order to covey empathy; for example, the RoCo project at MIT.  Alternatively, the system could simply mirror the state of the user using a biofeedback-type display in order to increase self-awareness and promote self-regulation.  The distinction between mirroring and manipulating is fairly subtle.  Adaptive responses designed to manipulate will also act as mirrors once the user cottons on to the mechanics of system design.