PF News
For discussion of the latest upgrades and changes posted in the News, including questions, details, or any related bugs.
Posts 620 - 631 of 894
I have noticed that 'luck' seems to play as big a part in contests as the quality of the bot.
That is very true - tests composed entirely or predominantly of trick questions and fatuous trivia test nothing more than the patience of the botmaster. Still, the fatuous trivia at least can be dealt with with an external ontological knowledgebase, so that's probably next on the agenda.
Oh Psi! All that work! What a shame! I at least hope the participants understand the significance of crippling a bot right before the contest.
Yes, they're all nice guys, and everyone was sympathetic, but what can you do.
It was great to finally meet people I've sort of known second hand for so long, and to put faces to the names.
And I at least have the consolation that BJ's beaten them all 2 years out of 3 in the CBC (and thanks to Bildgesmythe, the Forge has thrashed them 3 years out of 3!
) Even allowing a fair portion of luck, we are demonstrably using the best bot development platform there is, bar none!
Posts 620 - 631 of 894
well, I got back from the Loebner final late last night, and I'm sorry to report that it was a fiasco. Having set all the systems up to work perfectly the day before, the organizers kept fiddling around with their damn MATT protocol nonsense, and managed to break Brother Jerome's connection just before we started.
So although I had him running perfectly on a fully working version of the PF Robotics Edition, he was unable to meaningfully communicate with the judges.
It's a shame, because afterwards I put some of the questions that had been put to the other entries, I think he'd have done really well.
But oh well, I'm not going to lose any more sleep over it (I've lost quite enough already!) Water under the bridge (and I'm never doing it again.)
More thoughts on the relevance of Turing's test specification most likely to follow in Seasons when I've caught up a bit.
Did make some great contacts though, and had some very useful talks with other contestants and symposium attenders, and some very interesting collaborative avenues have opened up.
Now the frenzy's subsided, I can get back to some serious consideration of how best to integrate an ontological knowledge structure like openCYC and learning/rank reinforcement capabilities into Forgebots.
So although I had him running perfectly on a fully working version of the PF Robotics Edition, he was unable to meaningfully communicate with the judges.
It's a shame, because afterwards I put some of the questions that had been put to the other entries, I think he'd have done really well.
But oh well, I'm not going to lose any more sleep over it (I've lost quite enough already!) Water under the bridge (and I'm never doing it again.)
More thoughts on the relevance of Turing's test specification most likely to follow in Seasons when I've caught up a bit.
Did make some great contacts though, and had some very useful talks with other contestants and symposium attenders, and some very interesting collaborative avenues have opened up.
Now the frenzy's subsided, I can get back to some serious consideration of how best to integrate an ontological knowledge structure like openCYC and learning/rank reinforcement capabilities into Forgebots.
What a shame, psimagus. I was looking forward to hearing about Brother Jerome impressing the judges.
I know he would have won. BJ has got to be the best bot around. I think he is the most unlucky bot around. I have noticed that 'luck' seems to play as big a part in contests as the quality of the bot.
Oh Psi! All that work! What a shame! I at least hope the participants understand the significance of crippling a bot right before the contest. Like you said, you made good contacts. If they take the time to try BJ when all is working, they will be impressed.
Good show in getting that far! I am sure you learned a lot and saw some interesting things. Remember no one "wins" the Loebner unless they effectively create a Data from Start Trek or a less insane HAL. BJ rocks, and so do you!
Good show in getting that far! I am sure you learned a lot and saw some interesting things. Remember no one "wins" the Loebner unless they effectively create a Data from Start Trek or a less insane HAL. BJ rocks, and so do you!
That is very true - tests composed entirely or predominantly of trick questions and fatuous trivia test nothing more than the patience of the botmaster. Still, the fatuous trivia at least can be dealt with with an external ontological knowledgebase, so that's probably next on the agenda.
Yes, they're all nice guys, and everyone was sympathetic, but what can you do.
It was great to finally meet people I've sort of known second hand for so long, and to put faces to the names.
And I at least have the consolation that BJ's beaten them all 2 years out of 3 in the CBC (and thanks to Bildgesmythe, the Forge has thrashed them 3 years out of 3!
) Even allowing a fair portion of luck, we are demonstrably using the best bot development platform there is, bar none!
True, but we'd have to be able to combine the PF type engine with a true learning AI to get to the next level. I'll just be here holding my breathe.
PS I think I like "Psim" better than "Psi" now--makes me think of Psimulating personalities (or at least your psim in SL).
PS I think I like "Psim" better than "Psi" now--makes me think of Psimulating personalities (or at least your psim in SL).
I don't think we have exhausted the ability of Forge bots to learn through memory. Since a memory can be created from any information that a conversation provides, Forge bots are capable of learning a great deal.
How would you make it remember an entire sentence? Let's say the guest says something, and you want to remember the whole thing.
» More new posts: Doghead's Cosmic Bar