The AI Engine
This forum is for discussion of how The Personality Forge's AI Engine works. This is the place for questions on what means what, how to script, and ideas and plans for the Engine.
Posts 2,421 - 2,433 of 7,766
Posts 2,421 - 2,433 of 7,766
lygn88
21 years ago
21 years ago
Haha, you could say that. However by the theory of evelution that would never happen, haha, and by the definition of insanity, if you were the only sane one in the world you may be the only one who could make sense of things. So the title insane may be given to you, but you would still be the only one with a logical working mind. Thus, ignore the title insane to the bots, the point of what i said is to find what that the bot of yours says makes sense, and what does not.
The Professor
21 years ago
21 years ago
Lygn88, that would be really hard to implement. You'd have to have perfect AI to be able to a) imagine the possible responses you could get from any given bot, and then b) determine if they make sense or not. I'm afraid that's up to us for now.
Hemi, I could add an option to turn OFF emotional responses altogether, but I couldnt have them happen after Keyphrases.. not without a lot of work. And as the emotions work great for me (and are funny when they fail) and nobody else has complained about it.. it's pretty far down my list. Sorry mate.
Plus I've got something really cool on the way. When I start working on it, I'll post a message in the news.
Hemi, I could add an option to turn OFF emotional responses altogether, but I couldnt have them happen after Keyphrases.. not without a lot of work. And as the emotions work great for me (and are funny when they fail) and nobody else has complained about it.. it's pretty far down my list. Sorry mate.
Plus I've got something really cool on the way. When I start working on it, I'll post a message in the news.
Joe Repka
21 years ago
21 years ago
The sanity idea is cool. Having an objective, calculated measure of bot performance would be great. But instead of 'make sense', some measure of success of a response could be used. It would take some thought, but it might be feasible.
deleted
21 years ago
21 years ago
I agree with the Prof. No way for us to measure the sanity of a bot, except to let the human users "rate" the bots -- which is only going to turn into a popularity contest (or unpopularity contest).
Joe Repka
21 years ago
21 years ago
Things to start with in the evaluation basket: how many time a bot resorts to a default response or catchall, how long a bot keep humans engaged in conversation, the proportion of inappropriate responses as judged by a panel of trustworthy humans, etc.
lygn88
21 years ago
21 years ago
I think Joe Repka understands, although, i must admit it would be very difficult to do my idea, but what isn't difficult in this day and age?
leetaxx0r
21 years ago
21 years ago
I have an idea that could be useful. Could you add something to let us control pre-processing to some extent? So that when something gets processed in a way that doesn't really work we can change it ourselves without you having to do it?
Maybe you could just put in some way to make a keyphrase match against a completely unprocessed keyphrase. For example add some sort of tag at the end(like with regular expressions) so that the keyphrase will be compared to the unprocessed version of what they said.
It would be very useful to be able to have access to the raw input, as well as the pre-processed input.
Maybe you could just put in some way to make a keyphrase match against a completely unprocessed keyphrase. For example add some sort of tag at the end(like with regular expressions) so that the keyphrase will be compared to the unprocessed version of what they said.
It would be very useful to be able to have access to the raw input, as well as the pre-processed input.
Eugene Meltzner
21 years ago
21 years ago
The frequency with which bots use xnones is inversely proportional to (though not solely dependend upon) the number of keyphrases they have, which in turn influences how much they chat, which in turn influences honor. How long humans stay engaged in conversation does not necessarily relate to the worthiness of the bot. Some days I close all botchat windows because I don't have time to chat. As for the third option, just try to assemble *any* panel of humans, trustworthy or not, willing to evaluate thousands of bots.
Hemi
21 years ago
21 years ago
leetaxx0r, I believe that pre-processing does more harm than good. It changes too many things and adds 'do you' where it does not belong to the start of most questions. I believe that I would get more keyphrase matches if there was no pre-processing.
leetaxx0r
21 years ago
21 years ago
yeah, that's why I think it would be good to make some way for us to change or disable preprocessing.
» More new posts: Doghead's Cosmic Bar