We've mentioned the arbitrary nature of the megapixel war before, but only in general analogies. Ross at the Petravoxel blog gets precise and provides proof on why going over 7 megapixels in a point-and-shoot makes absolutely no sense.
To try and sum up Ross's reasoned and technical argument against camera companies shoving more and more megapixels down the buying public's throats, it's about what happens when you make pixels teensy-weensy in an effort to cram a (nominal) 12 million of them into one exposure. When light is captured in pixels at microscopic sizes, it's focused not in a sharp pinpoint of clarity, but a fuzzy bulls-eye pattern, named the "Airy disk" and showing up all over your photo.
Camera manufacturers aren't blind to this, but their efforts to fix it, in models such as the Olympus FE-26, often backfire:
The FE-26 is a "12 megapixel" model (actually it's more like 11.8 Mp) using a 1/2.33″ sensor. This means each pixel is about 1.5 microns wide. When pixels are that small, the random difference in photon counts between adjacent pixels can add quite a bit of noise to the image. To solve this, the camera's processor chip applies a noise-suppressing algorithm, which unfortunately smears out all the fine detail and texture in the scene.
Read Ross's post and its backlinks for a more mathematical and photo-minded take on "The Great Megapixel Swindle", and walk away with the knowledge that, though your four-year-old digital camera may seem outdated, trading up may actually hurt your ability to capture crisp images.