2008/5/17 Steve Richfield <[EMAIL PROTECTED]>: > Will, > > I have read and reread your posting and still there are some ambiguities in > your meaning. Hence, I will presume (perhaps wrongly) to understand what you > are saying and respond. If I misunderstood, then please feel free to correct > me... > > On 5/16/08, William Pearson <[EMAIL PROTECTED]> wrote: >> >> 2008/5/16 Steve Richfield <[EMAIL PROTECTED]>: >> > Does anyone else here share my dream of a worldwide AI with all of the >> > knowledge of the human race to support it - built with EXISTING >> > Wikipedia >> > and Dr. Eliza software and a little glue to hold it all together? >> > >> >> I'm taking this as a jumping off point to try and describe and expand >> upon something I have been mulling over whilst reading your messages. >> >> I think you and Matt are interested in solving the oracle problem. >> That is going to one entity for answers to general questions. > > > I don't think so. Dr. Eliza is designed to respond to complex problem > statements. Being too general just gets a pile of questions to de-generalize > the problem statement.
I didn't mean general in that sense, I should have tried to have found a better word. I meant common problems that have a common solution between people and times. >> >> I am >> interested in solving more personal problems. That is there are >> problems that are unique to the individual at each time. >> >> The search problem is a good example. To present the optimal search >> for an individual you must have as much data about the individual as >> possible. For example if the search engine knew I had been talking to >> you it would return different results when I searched for Dr. Eliza >> (assuming google knows anything about your system). As I would not be >> comfortable with this level of information being known about me, a >> centralized search oracle will not work (I will have to stop using >> gmail when AI gets too advanced). > > > I suspect that a capability that includes automatically appending your > entire autobiography onto any problem statements would do this job handily. Since I don't keep an autobiography this might prove somewhat of a problem. >> >> The problems essence is finding pertinent information and presenting >> it at the right time to the user. I shall call it the whisperer class >> of problems for the moment. I am also strongly interested in Augmented >> Reality, where knowing when to interrupt you with emails and other >> communications is an important thing for the system to do. > > > I don't see how this would fit in. An augmented reality system has a certain amount of knowledge about the situation you are in, it has to make a decision about whether you need to know about a piece of information it has acquired (via email, IM or through it scraping the web) in this situation. If it can't make this decision well it will forever be annoying you by popping up alerts at inappropriate times. Don't alert you to friends lewd but funny picture during a meeting, but do alert you to some negative news from a newspaper about your company. It is a question of what data you want to get and when. >> >> Both types of system are important, I don't think I can do a decent >> whisperer system with current technologies, including Dr Eliza. Not to >> denigrate your approach, but to acknowledge that there are more types >> of problems out there to be solved. > > > Yes. Dr. Eliza is NOT a fit replacement for a search capability, where there > is no difficult problem to solve, but instead the user just wants to > retrieve some data. Not some data. The *correct* data. That is difficult and valuable. Else google wouldn't have been able to have taken over yahoo. > However, many people (including myself) use search > capabilities to solve in days/weeks/months problems that should just take > minutes (at most) to solve. My own spending 4 full-time months on what > should have been a 10 minute problem solving was my own motivation to create > Dr. Eliza. So search isn't perfect but doesn't need to be solved? Will Pearson ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=103754539-40ed26 Powered by Listbox: http://www.listbox.com
