how it works, copied from their site:
Since launching, this site sparked up some discussion as to how it all works. Ofcourse, we don’t want to disclose too much of the ‘algorithm’ (it's not all that high-tech) of the site. However.. basically it searches based on associative (english!) sentences. The given searchterm is used in these sentences which are then sent off to the search engine, counting the amount of results returned. (Sentences are double quoted before they are sent off, so as to make sure the search-enginges search for occurances of the *whole* sentence).
This, ofcourse, produces questionable results which – considering the varying results per day/hour – should not be taken very seriously. However, the more results returned, the more reliable these results can become. Do a search for George Bush and then Barack Obama, and you’ll see that the internet is certainly not far off – or perhaps even in-sync – with the result you had in mind.
Doubtful? My advice: sum up 10 ‘obvious’ searches, of which you are almost certain of the results (like ‘beer’, ‘love’, ‘sleeping’, etc.) and then enter 10 less obvious searches into the search field. If the first 10 convince you of accurate results, the second 10 will perhaps be not as random as you thought!
