The foregoing is an example of the difficulties that come up when an innocent ventures into image restoration. (And incidentally, the astronomical answer in this case is awfully important.) But let me conclude by emphasizing this position of innocence and ignorance. The average user of HST images knows even less than I do. One can of course argue that a good scientist learns whatever he or she needs to know in order to get meaningful answers. But there is a limit to how many things a person can become expert in, and the more time that you spend learning abstruse methods of image reconstruction - and especially the practical details that you need to know to make them work - the less time there is to reduce and measure those voluminous images. So my real message is that you experts need not only to devise elegant and powerful methods of image restoration; you need also to make them accessible, and even transparent, to the ordinary HST observer - without the danger that he or she will unwittingly produce wrong answers without knowing it. May I remind you of the phrase ``user-friendly''?