Specifications are for Reasoning From

We write specifications of systems in order to be able to reason about those systems.  This reasoning can be formal or informal. It can take the form of proving properties, deriving properties or refining the specification to code.  The purpose of specifications is to allow this reasoning to take place, ie: specifications are for reasoning from.  Looking at specification this way leads me to make the following suggestions:

• Specifications should be written in a way that makes reasoning easy.  A way to do this is to write them as conjunctions of ready-to-use proof steps, with the pre-conditions and variables of each step clearly visible.
• Conciseness is not necessarily important in specifications.  Not including irrelevant material is important, as is clearly laying out the relevant material, but using abstruse theories to make the specification as short as possible is not.
  
• Graphical notations that have not been designed with reasoning in mind should be avoided.  Just because a notation is graphical does not mean that it makes reasoning easy.
  

Stargazing by Peter Hill

I only picked up this book because of its title.  I only bought it because, when I opened it, I came across a mention of the island of Pladda.

Back in in the summer of 1972, when I was 13, our family spent three weeks staying with friends on the Isle of Arran.  That holiday was to me rather like what the trip to Corfu was for the young Gerald Durrell in My Family and Other Animals, except that it wasn't wildlife that interested me then, but stars.  Because of the lack of street lamps the skies were darker than any I had seen before and, because of the sea horizon, I could actually see stars further south than I could from back in Cleveland.  And the views of the Milky Way through binoculars were simply breathtaking.  On my return from that holiday I joined the British Astronomical Association and took up variable star observing in earnest. 

Although we were based at Pirnmill, in the north-west corner, we explored all parts of the island, and often from the mountains or from the southern shore-line the islands of Pladda and Ailsa Craig were visible in the distance.  Pladda was small, flat and close in, Ailsa Craig, large, hemispherical, and much further out, down the Firth of Clyde.

In the following summer, that of 1973, Peter Hill, an art student from Dundee, took a holiday job as a lighthouse keeper and spent a few weeks on Pladda and then a few more on Ailsa Craig.  Stargazing is his account of that time, of the characters he worked with, the way of life, and the things that happened to him.  It is an enjoyable, heart-warming read. I am sure that would have lead to hordes of people applying to work as lighthouse keepers, if only the lighthouses hadn't all been automated by now.