Jono DiCarlo, of Humanized, wrote Are Adaptive Interfaces the Answer?:
What was the problem? Adaptive interfaces have several drawbacks, and the big one is that they're intrinsically hard to learn. If you're trying to learn an adaptive interface, you have to chase after a moving target: "Where did that menu item go? It was here yesterday...". Even a user experienced with the interface will have a hard time habituating to it, since the locations of commands are not consistent. It's an interface that moves in the night.
A good and insightful article as a whole, however, Jono DiCarlo falls short on the possible reason for adaptive interfaces are hard to learn. Even though he actually mention "where did it go?" Todays graphical user interfaces are, graphical (well, of corse they are). They give the user a spatial way of mentally organizing their knowledge on how the interface works and where their stuff are and where to find functionality.
Actually, few interfaces are completely spatial, most are semi-spatial (for good or bad, however that is a subject for another time), but most stuff stay where they are. Therefore, remembering the place of something is easy. It is when that thing suddenly is not there anymore that the user get confused.
Not all adaptive interfaces are bad, handwriting recognition has since long proven to apply adaptive methods to improve performance. That takes me to the point: if the user does not have to learn something new when the system adapts, the interface stays the same in the eye of the observer.
So instead of that, we prefer to have Enso's behavior change only when the user tells it to change. Remember that you can "UNLEARN" any Open command -- even Open commands that Enso found in your Start menu. This lets you customize any Open command. So for instance, if you don't like typing "Open Microsoft Word", you can do "Unlearn Open Microsoft Word", and then "Learn As Open Word" or even "Learn As Open W".
I would like to disagree, Enso would do just fine being adaptive, responding to frequent user actions because there are no spatial elements in the Enso interface such as those found in the Microsoft Office menus. Actually, the Enso interface is more akin to verbal communication and behavior than most other interfaces. The functionality where the user explicitly teaches Enso to do stuff could very well live side by side with an adaptive interface.
