"Guido van Rossum" <guido at python.org> wrote in message news:ca471dc20604241106x6719551eo5318aae9da8075b1 at mail.gmail.com... > On 4/24/06, Alex Martelli <aleaxit at gmail.com> wrote: >> I dislike that as much as I dislike [<genexp>] as a shorthand for >> list(<genexp>), but I have no trouble admitting that if we have the >> [...] form, it's consistent to have the {...} one too. >> I think you're atypical in that dislike. Like Greg and you, I would like to see sets treated the same way they might have been if included from the beginning in 1.0. The current situation is only understandable knowing their history as an add-on reflecting a slight relaxation of initial minimalism. Terry Jan Reedy