<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	>
<channel>
	<title>Comments on: I&#8217;m Squinting&#8230; But No Agents So Far</title>
	<atom:link href="http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/</link>
	<description>Seth Ladd's blog about Ruby on Rails and crunching data.</description>
	<pubDate>Fri, 09 Jan 2009 20:32:06 +0000</pubDate>
	<generator>http://wordpress.org/?v=MU</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Daniel E. Renfer</title>
		<link>http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/#comment-151</link>
		<dc:creator>Daniel E. Renfer</dc:creator>
		<pubDate>Thu, 29 Mar 2007 13:33:52 +0000</pubDate>
		<guid isPermaLink="false">http://204.14.242.104/?p=555#comment-151</guid>
		<description>&lt;p&gt;I use an online "agent" that once given a list of URLs, will periodically check those URLs, download new updates, parse the returned documents, sort, merge, and present the combined collection of objects ordered by update time. (or other criteria)&lt;/p&gt;

&lt;p&gt;I call it Google Reader.&lt;/p&gt;

&lt;p&gt;There are agents out there, but we're always quick to dismiss them as too simplistic. We're looking for that future vision of flying cars and missing all the smaller advancements we've seen.&lt;/p&gt;

&lt;p&gt;Also, I think the Atom Publishing Protocol will open the doors for a lot of the agent to agent interactions. (My dentist would accept an Atom Entry containing iCal or xCal markup to schedule my appointment)&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>I use an online &#8220;agent&#8221; that once given a list of URLs, will periodically check those URLs, download new updates, parse the returned documents, sort, merge, and present the combined collection of objects ordered by update time. (or other criteria)</p>
<p>I call it Google Reader.</p>
<p>There are agents out there, but we&#8217;re always quick to dismiss them as too simplistic. We&#8217;re looking for that future vision of flying cars and missing all the smaller advancements we&#8217;ve seen.</p>
<p>Also, I think the Atom Publishing Protocol will open the doors for a lot of the agent to agent interactions. (My dentist would accept an Atom Entry containing iCal or xCal markup to schedule my appointment)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Thomas</title>
		<link>http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/#comment-150</link>
		<dc:creator>Thomas</dc:creator>
		<pubDate>Thu, 15 Mar 2007 07:34:56 +0000</pubDate>
		<guid isPermaLink="false">http://204.14.242.104/?p=555#comment-150</guid>
		<description>&lt;p&gt;My mom would say "Thomas, go outside. Leave the agents for now".&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>My mom would say &#8220;Thomas, go outside. Leave the agents for now&#8221;.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Drew</title>
		<link>http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/#comment-153</link>
		<dc:creator>Drew</dc:creator>
		<pubDate>Sat, 10 Mar 2007 03:15:59 +0000</pubDate>
		<guid isPermaLink="false">http://204.14.242.104/?p=555#comment-153</guid>
		<description>&lt;p&gt;I'd call a google-searching cron job an agent. It seems like it meets your definition, although the action it does is not very impressive, and it happens to have minimal reasoning/clarification abilities. But you could make a slightly fancier one that does talk to you/google/someOtherSite for clarifications. Or you could add the ability to gather new keywords from your IM logs, so the agent learns something about what you care about.&lt;/p&gt;

&lt;p&gt;Do the airfare-search websites count as agents? I think some of them will even do part of their search and then ask you for clarification before they can finish.&lt;/p&gt;

&lt;p&gt;I generally agree with you: I want more agents; I want them to use RDF for their data; I want them to take over more and more of each task as I input more data about myself. But I also suspect that these ideal agents will appear quite gradually, and the cron job is just an early form.&lt;/p&gt;

&lt;p&gt;By the way, some people are already dazzled by the google cron job :)
http://dilbertblog.typepad.com/the&lt;em&gt;dilbert&lt;/em&gt;blog/2007/03/too&lt;em&gt;frickin&lt;/em&gt;coo.html&lt;/p&gt;

&lt;p&gt;cheers-
Drew&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>I&#8217;d call a google-searching cron job an agent. It seems like it meets your definition, although the action it does is not very impressive, and it happens to have minimal reasoning/clarification abilities. But you could make a slightly fancier one that does talk to you/google/someOtherSite for clarifications. Or you could add the ability to gather new keywords from your IM logs, so the agent learns something about what you care about.</p>
<p>Do the airfare-search websites count as agents? I think some of them will even do part of their search and then ask you for clarification before they can finish.</p>
<p>I generally agree with you: I want more agents; I want them to use RDF for their data; I want them to take over more and more of each task as I input more data about myself. But I also suspect that these ideal agents will appear quite gradually, and the cron job is just an early form.</p>
<p>By the way, some people are already dazzled by the google cron job  <img src='http://s.wordpress.com/wp-includes/images/smilies/icon_smile.gif' alt=':)' class='wp-smiley' /><br />
<a href="http://dilbertblog.typepad.com/the" rel="nofollow">http://dilbertblog.typepad.com/the</a><em>dilbert</em>blog/2007/03/too<em>frickin</em>coo.html</p>
<p>cheers-<br />
Drew</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Lyle</title>
		<link>http://blog.semergence.com/2007/03/08/im-squinting-but-no-agents-so-far/#comment-152</link>
		<dc:creator>Lyle</dc:creator>
		<pubDate>Fri, 09 Mar 2007 17:26:00 +0000</pubDate>
		<guid isPermaLink="false">http://204.14.242.104/?p=555#comment-152</guid>
		<description>&lt;p&gt;I think that at least part of the problem is that the software tools that exist for developing agents aren't easy enough for just anyone to use. My dentist doesn't have a scheduling agent, and he's certainly not going to pay some software developer to develop and deploy such an agent for him -- how would that make any business sense for him?&lt;/p&gt;

&lt;p&gt;Online services like Blogger, flickr, Wikipedia and yes, MySpace, are successful because they provide tools that someone with little or no programming experience can use. As long as developing autonomous, reasoning agents is restricted to software developers who can grok RDF and OWL, you're just not going to see mainstream agent deployment.&lt;/p&gt;</description>
		<content:encoded><![CDATA[<p>I think that at least part of the problem is that the software tools that exist for developing agents aren&#8217;t easy enough for just anyone to use. My dentist doesn&#8217;t have a scheduling agent, and he&#8217;s certainly not going to pay some software developer to develop and deploy such an agent for him &#8212; how would that make any business sense for him?</p>
<p>Online services like Blogger, flickr, Wikipedia and yes, MySpace, are successful because they provide tools that someone with little or no programming experience can use. As long as developing autonomous, reasoning agents is restricted to software developers who can grok RDF and OWL, you&#8217;re just not going to see mainstream agent deployment.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
