Re: Artificial Intelligence: "The Remembrance Agent"

[Will Dockery]

On Dec 13, 3:24 pm, 0x0000 <zero_...@yahoo.com> wrote:
>
> +gnu.misc.discuss +alabama.general -alt.arts.poetry -rec.arts.poems
>>Will Dockery wrote:
> > This was sent to me by a friend, anyone know of this, and how
> > effective it is as far as AI development?
>
> > "...I ran across something here you might be interested in, it's
> > called "The Remembrance Agent" -
>
> >> The Remembrance Agent is one of the projects being developed by
> >> the MIT Media  # Lab's software agents group.  Given a collection
> >> of the user's accumulated     a email, Usenet news articles,
> >> papers, saved HTML files and other text notes, it a attempts to
> >> find those documents which are most relevant to the user's
> >> current a context.  That is, it searches this collection of text
> >> for the documents which a bear the highest word-for-word
> >> similarity to the text the user is currently    a editing, in the
> >> hope that they will also bear high conceptual similarity and   a
> >> thus be useful to the user's current work. These suggestions are
> >> continuously  a displayed in a small buffer at the bottom of the
> >> user's emacs buffer.  If a    a suggestion looks useful, the full
> >> text can be retrieved with a single command. a
>
> >http://www.remem.org/
>
> > I just installed this software package (remembrance) on the upstairs
> > computer and am going to start "training" it.  I can set this up so
> > you can create a document repository - or possibly use an existing
> > one (e.g. wikinfo)  to train it on your own stuff...  It could
> > conceivably be integrated into a "chat-bot" type app, as well - if
> > you're interested, let me know, and I'll start working on it.

Sounds good... now three or four AI that could interact and create
music and words for /listenable/ songs would be anther step, on down
the line, maybe.

> >[snipped unrelated content]

--
Paxworth Projects:
http://www.zerohex.com/paxworth-projects/