Java developers have converted a neural network interface to act as a second pair of eyes while playing Warcraft
Defense of the Ancients is a scenario for Warcraft 3 that is heavily influenced by Starcraft, and the map "Aeon of Strife". However, it does have a eye blistering array of differing spells to use, and micro-managing has been somewhat of a nightmare until now.
The DOTA Autoscript uses a neural network (similar to your own brain) to analyze, decipher and queue actions happening on screen. While the script is running in the background, it keeps a constant watch on what's happening and runs it through its own expert system to determine what your best course of action is.
All this is done purely on what is on screen, rather than triggers in the programming. The beauty of this neural network though is that because it works graphically, it can use a recognition system to understand what buffs are where, even if you change the screen size. It also can recognize a "recharging" buff as well, so it can be ready for use as soon as it recharges.
To give you a taste of its versatility, pressing one key activates the entire expert system to queue up all available attack spells on the current target, which will all release as soon as they finish recharging.
If you're defending though, the text to speech interface will tell you just before your defensive spells are extinguished, so that you can immediately bring them back up to strength.
How it does that is explained on the site (with reference to Paris Hilton, no less) but it does leave one question.
Who's actually playing the game at this point?