Slashdot Mirror
Domain: earthspace.net
Stories and comments across the archive that link to earthspace.net.
Comments · 6
-
Re:whats the point
Yep - many of the xboxes will be bought by the linux/*bsd geeks who will install linux on them for a cool TV-TypeWritter
-- -
When in doubt, ask.
"Enter a check", huh?
IMHO, before somebody solves the 'strong AI problem', the computer could quite simply ask the user:
"Do you want to enter a financial check, make an illegal chess move or make a constraint in the program you are writing?"
The system should always calculate an amount of ambiguity for each statement, and if the action is clear enough, execute it. If not, then ask for clarification.
As for the story of "delete *$" here, some commands should be marked more "dangerous" than others. In these cases confirmation should be asked much more often than in non-dangerous activities. -
When in doubt, ask.
"Enter a check", huh?
IMHO, before somebody solves the 'strong AI problem', the computer could quite simply ask the user:
"Do you want to enter a financial check, make an illegal chess move or make a constraint in the program you are writing?"
The system should always calculate an amount of ambiguity for each statement, and if the action is clear enough, execute it. If not, then ask for clarification.
As for the story of "delete *$" here, some commands should be marked more "dangerous" than others. In these cases confirmation should be asked much more often than in non-dangerous activities. -
Re:Consider the audience.But for people who don't work with computers all day long, saying something like "Enter a check," "Open a new document," or "Send an e-mail" will do just fine.
"Enter a check", huh?
The chess 'bot would wake up and tell you
Sorry Dave, I can't let you do that. Chess rules specifically forbid entering a check.
Seriously, ambiguity is a big problem with natural-language interfaces. How is the computer to know if you wanted to do something involving your checking account or if you want to add an integrity constraint to a computer program you are writing? Or if you are playing a chess game and trying to make an illegal move
Natural language comprehension is an AI-complete problem. That doesn't mean useful approximations can't be done. But they only work if you keep commands simple and adhere to a computer-friendly style of expression. With requests of any complexety the risk of a misunderstanding is too great to trust interface to do anything that can't easily be undone. In this sense it is similar to DWIM interfaces (follow the link for a good anecdote).
No doubt natural language interfaces will find its niches, and someday many people may even be using natural language interfaces exclusively. But when these people need to do something more complex or risky, they will need to turn to a hacker who masters some other arcane but concise command language.
/A
-
Re:Consider the audience.But for people who don't work with computers all day long, saying something like "Enter a check," "Open a new document," or "Send an e-mail" will do just fine.
"Enter a check", huh?
The chess 'bot would wake up and tell you
Sorry Dave, I can't let you do that. Chess rules specifically forbid entering a check.
Seriously, ambiguity is a big problem with natural-language interfaces. How is the computer to know if you wanted to do something involving your checking account or if you want to add an integrity constraint to a computer program you are writing? Or if you are playing a chess game and trying to make an illegal move
Natural language comprehension is an AI-complete problem. That doesn't mean useful approximations can't be done. But they only work if you keep commands simple and adhere to a computer-friendly style of expression. With requests of any complexety the risk of a misunderstanding is too great to trust interface to do anything that can't easily be undone. In this sense it is similar to DWIM interfaces (follow the link for a good anecdote).
No doubt natural language interfaces will find its niches, and someday many people may even be using natural language interfaces exclusively. But when these people need to do something more complex or risky, they will need to turn to a hacker who masters some other arcane but concise command language.
/A
-
Re:A promiseTo All: Oh Lord. Do you see what I mean? To this Anonymous Coward, that's the only definition of the word he knows.
To Anonymous Coward: Most of the people who post on SlashDot use the geek culture definition of the word. To them, a hacker isn't someone who breaks into computers. That's a cracker. I won't try to define hacker: it's done much better here