CZ Talk:Bots

This is a reasonable start. I notice that wikipedia has done a thorough job. It also includes things like "minor edits" and "approval", etc., etc.. How many of these do we want to use? Do we need to re-invent the wheel?

I think the main thing is to make sure anyone that is affected will have a chance to give input. It seems that the onus should be placed on the bot producer to advise those that it is going to affect, rather than expecting those that it is going to affect to check in here to make sure we aren't going to mess with their article? D. Matt Innis 23:54, 20 September 2009 (UTC)

There is no "their article" here, I think, and any edit in this wiki should be regarded as a Be bold edit unless it causes some sort of damage (to page content, formatting or contextualization, or to other users). Of course, undoing bot edits is tedious, and the onus should be on the bot operator to do it if necessary, for which precautions can be taken (e.g. bot-specific categories). But if it is clear that failure to do so would result in a ban, it is unlikely that we are going to see multiple such cases. There is no need to reinvent the wheel, and I think the bot policy at the English Wikipedia is a useful starting point (that's why I had put it in), but if we have to differ from them, then our policy should be more liberal than their's, since the main reason for their strictness is that they do not use an entry check and bots could thus, technically, be operated from multiple bot-created accounts and cause massive damage. Here, only one account per user is possible (or a few more should bot accounts ever be permitted), so keeping misuse at bay really should not be the problem. --Daniel Mietchen 20:24, 28 September 2009 (UTC)

Well, I would suggest that we start strict and loosen the reigns as we see how it works. I don't think it is reasonable for us to expect that the bot programmer can think of all the potential problems that their bot might produce, so right off the bat, we need to assure that they will be documented and tested before they are run. How can this be done? Could we require that the bot be tested on, say 50 articles or so... then review the changes before moving on. I assume this is soemthing that you already do. All we need to do is document it. Is this already done? If so, where? D. Matt Innis 02:07, 29 September 2009 (UTC)