How many thoughts can you think?

In ordinary computer programmes, the relationship between data in a machine and the concepts it represents is de ned arbitrarily by the programmer. It is argued here that the Strong AI hypothesis suggests that no such arbitrariness is possible in the relationship between brain states and mental experiences, and that this may place surprising limitations on the possible variety of mental experiences. Possible psychology experiments are sketched which aim to falsify the Strong AI hypothesis by indicating that these limits can be exceeded. It is concluded that although such experiments might be valuable, they are unlikely to succeed in this aim. 1 The argument in brief The Strong AI hypothesis [2], is that a mind is associated with any suitably sophisticated machine 1 . Given this, it seems reasonable to presume furthermore that any speci c mental experience is associated with (or `produced by') one or more speci c machine states or state trajectories. The number of distinct possible mental experiences must therefore be limited by the number of possible machine state trajectories. The set of possible machine state trajectories may be a continuum, and therefore in nite, but it can be reasonably argued that a nite subset of these is entirely representative so far 1 Strong AI asserts that algorithms underlie consciousness. Here a less speci c hypothesis is adequate { that consciousness arises from certain patterns formed in the brain's activity.