Bot Technology

The implementation of a pair of bots remains problematic. Not for the same reasons as before - those were purely technical. That sort of problem can be addressed with a combination of tenacity, research, expert networking, and cash. Having tried all of these approaches I now have a couple of viable solutions.

The first is to 'employ' the computing research guys at Newcastle to set up the bots on a research server. The only downside to that solution is that I would be need to develop a work method for writing and updating the AIML sets. Being one step removed from owning the server I would need to be get some kind of administrator access - this is not the sort of thing server admin people are very keen on.

The second is to use the 'commercial' site that provides the Pandorabot. I already have a test bot up there and I've found an Flash/Actionscript interface (thanks to Jamie Durrant) that will talk to the Pandorabot server. Cool! This is one comparatively small step away from have two Pandorabot accounts and using the Flash interface to throw output to input from one bot to the other. The advantage of Panadora bot is that I could easily update the AIML and be able to speak to each of the bots individually.

I'll keep playing with the Actionscript to see what I can do.