Reading this and some other threads about using AI for projects I still don't have much idea of what they are really ready and able to do.

I have recently read this paper about developing autonomous bots for CoffeeMUD, which seems like something I could definitely use:

https://e-archivo.uc3m.es/rest/api/core/bitstreams/7452b84e-a307-48c0-ba12-99cd4c15de09/content

I had been thinking maybe one can just tell some AI or other to read that paper then telnet to a CoffeeMUD server and "be" such a bot, or maybe to fire itself up a tinyfugue or other MUD client and use that "as" such a bot, rather than asking it to write code, for example tinyfugue macros and triggers, to implement such a bot?

But revieingreviewing this thread I am now dubious it could write tinyfugetinyfugue (or other MUD client) macros-and-triggers (in sum, scripts) to implement such a bot.


Other vague ideas in back of my mind make me think maybe the AIs also likely cannot do things like go log in somewhere to do something, right? Some kind of prevent them being used to attack other servers etc protection / ethics?


-MarkM-

Reading this and some other threads about using AI for projects I still don't have much idea of what they are really ready and able to do.

I have recently read this paper about developing autonomous bots for CoffeeMUD, which seems like something I could definitely use:

https://e-archivo.uc3m.es/rest/api/core/bitstreams/7452b84e-a307-48c0-ba12-99cd4c15de09/content

I had been thinking maybe one can just tell some AI or other to read that paper then telnet to a CoffeeMUD server and "be" such a bot, or maybe to fire itself up a tinyfugue or other MUD client and use that "as" such a bot, rather than asking it to write code, for example tinyfugue macros and triggers, to implement such a bot?

But revieing this thread I am now dubious it could write tinyfuge (or other MUD client) macros-and-triggers (in sum, scripts) to implement such a bot.


Other vague ideas in back of my mind make me think maybe the AIs also likely cannot do things like go log in somewhere to do something, right? Some kind of prevent them being used to attack other servers etc protection / ethics?


-MarkM-