Bot Pride
I am excited when things get emergent enough that I don't get why they work any more.
Try to imagine this is me chatting with a two-year-old.
Yeah, yeah, this is inextensible. There is no intermediate memory between how-to-respond-to-the-immediately-previous-statement and learning-a-permanent-pattern. So you can't have "conversation".
Specifically, how would I go about teaching reggie to count? What would that mean in this participants-alternate-sentences format? Any ideas?
Try to imagine this is me chatting with a two-year-old.
me: what is one plus one
reggie: is one plus one
me: :-(
reggie: one
me: one plus one is two
reggie: two
me: :-)
reggie: :-)
me: what is one plus one
reggie: one
me: :-(
reggie: :-)
me: what is one plus one
reggie: two
me: :-)
reggie: :-)
Yeah, yeah, this is inextensible. There is no intermediate memory between how-to-respond-to-the-immediately-previous-statement and learning-a-permanent-pattern. So you can't have "conversation".
Specifically, how would I go about teaching reggie to count? What would that mean in this participants-alternate-sentences format? Any ideas?
posted by Kevin at
10:24 PM
1 Comments:
this is so interesting as I do not know anything about chat bots. Conceptually if I was to design anything close to a chat bot I'd have immediate memory, and a more conceptual/learned memory. After that I'd have task definitions: if I wanted my boty to count, I'd ask it if it could count. Then my dear boty would parse the command count, and count for me (i.e. output the action I label as count). This is sort of unscalable. I wonder how they actually do it.
By
Anonymous, At
June 7, 2008 10:44 PM
Post a Comment
<< Home