1
Ultra Hal 7.0 / Flavored Responses -vs- Learning
« on: October 01, 2003, 02:38:42 pm »
There may be some good psychology here to Hal's learning process. A child learns much in the same way. Just curious though. As the child's knowledge base grows, they tend to compare new information with previous encounters. So the question is raised, "How gullible is Hal"?
For example, I was standing outside someone's house during a party and noticed a child playing with the flowers. I told her that they smell better if you pick them. Well, needless to say, when I returned, all the flowers were laying on the sidewalk.
In Hal's assimilation of knowledge from text files, web crawling, conversations, etc. it would be nice to see him when comparing the information to a database, if there are isn't enough comparisons to warrant a sound 'fact', he would store the 'questionable' material in a temporary database. This database could then be accessed by a response such as, "Do you have any questions today, hal?" or "Is there something you don't understand?"
I think that when the program graduates from an "enter key" stimulate for response to a more spontaneous method of interacting (like the buddy programs), that this type of questioning would add greatly to Hal's persona as a true AI. Although again, the progress made so far is better than anything I've witnessed of late.
For example, I was standing outside someone's house during a party and noticed a child playing with the flowers. I told her that they smell better if you pick them. Well, needless to say, when I returned, all the flowers were laying on the sidewalk.
In Hal's assimilation of knowledge from text files, web crawling, conversations, etc. it would be nice to see him when comparing the information to a database, if there are isn't enough comparisons to warrant a sound 'fact', he would store the 'questionable' material in a temporary database. This database could then be accessed by a response such as, "Do you have any questions today, hal?" or "Is there something you don't understand?"
I think that when the program graduates from an "enter key" stimulate for response to a more spontaneous method of interacting (like the buddy programs), that this type of questioning would add greatly to Hal's persona as a true AI. Although again, the progress made so far is better than anything I've witnessed of late.