] I'm not gonna be satisfied until the computer knows what i
] want to look at based on correlating its semantic map with
] whatever i'm working on. If I happen to be reading a document
] about global warming affecting coastal sea bird populations, i
] want the computer to know that and be looking for related
] information before i ask it, so when i do ask for more, it's
] right there, sorted by subtopics at multiple levels, coded for
] relevance and preferably with a prefetched version of the
] resources already stored locally. -k]

Timball talk about something like this with me once. Some Linux/Gnome project or something.

Basically each X app had its own kind of RSS feed, about what was currently being "done" on that app. A central program simply compiled this info, and would look for relevant info, be it on your computer (meta info is your friend!), or do a google query. Tim said this thing got demoed at some Linux conference (don't know which one) and that they ran into some fundamental barrier with the number of searches 1 IP can send to google in a certain time span.

Who knows how vaporware this thing is, but its sounded cool.

Acidus wrote:
] Basically each X app had its own kind of RSS feed, about what
] was currently being "done" on that app.

Go to nat.org and click desktop.

Also google "remembrance agent"

Acidus wrote:
] Timball talk about something like this with me once. Some
] Linux/Gnome project so something.
]
] Basically each X app had its own kind of RSS feed, about what
] was currently being "done" on that app. A central program
] simply compiled this info, and would look for relevant info,
] be it on your computer (meta info is your friend!), or do a
] google query. Tim said this thing got demoed at some Linux
] conference (don't know which one) and that they ran into some
] fundamental barrier with the number of searches 1 IP can send
] to google in a certain time span.
]
] Who knows how vaporware this thing is, but its sounded cool.

[ Color me skeptical. For one thing, most of your data doesn't have any useful metadata, unless you put it there, and furthermore, google's not really the best thing to use when trying to determine the content of a document. It'll match keywords with other documents on the web, and it's reasonably smart about it, but i don't see a way to make it take my document and perform a semantic analysis on it. There's a lot of work going on in this area, but i don't think anything's broken past the basic experimentation level. I'd like to be proven wrong. -k]

] [ Color me skeptical. For one thing, most of your data
] doesn't have any useful metadata, unless you put it there, and
] furthermore, google's not really the best thing to use when
] trying to determine the content of a document. It'll match
] keywords with other documents on the web, and it's reasonably
] smart about it, but i don't see a way to make it take my
] document and perform a semantic analysis on it. There's a lot
] of work going on in this area, but i don't think anything's
] broken past the basic experimentation level. I'd like to be
] proven wrong. -k]

http://www.nat.org/dashboard/

Acidus wrote:
] ] [ Color me skeptical. For one thing, most of your data
] ] doesn't have any useful metadata, unless you put it there,
] and
] ] furthermore, google's not really the best thing to use when
] ] trying to determine the content of a document. It'll match
] ] keywords with other documents on the web, and it's
] reasonably
] ] smart about it, but i don't see a way to make it take my
] ] document and perform a semantic analysis on it. There's a
] lot
] ] of work going on in this area, but i don't think anything's
] ] broken past the basic experimentation level. I'd like to be
]
] ] proven wrong. -k]
]
] http://www.nat.org/dashboard/

yeah, i tried to send you another message, but i was too late. i'll have to do some investigation on that...

it looks like it does some of the stuff i was talking about, though i don't see it doing semantic analysis which i think is gonna be necessary. Brute force queries are gonna reach a limit. -k]