From fork-admin@xent.com Wed Oct 2 18:18:59 2002 Return-Path: Delivered-To: yyyy@localhost.example.com Received: from localhost (jalapeno [127.0.0.1]) by jmason.org (Postfix) with ESMTP id DB3F816F03 for ; Wed, 2 Oct 2002 18:18:58 +0100 (IST) Received: from jalapeno [127.0.0.1] by localhost with IMAP (fetchmail-5.9.0) for jm@localhost (single-drop); Wed, 02 Oct 2002 18:18:58 +0100 (IST) Received: from xent.com ([64.161.22.236]) by dogma.slashnull.org (8.11.6/8.11.6) with ESMTP id g92GuEK17987 for ; Wed, 2 Oct 2002 17:56:14 +0100 Received: from lair.xent.com (localhost [127.0.0.1]) by xent.com (Postfix) with ESMTP id 0E6C0294175; Wed, 2 Oct 2002 09:56:03 -0700 (PDT) Delivered-To: fork@example.com Received: from hotmail.com (dav23.law15.hotmail.com [64.4.22.80]) by xent.com (Postfix) with ESMTP id BDEC529409C for ; Wed, 2 Oct 2002 09:55:26 -0700 (PDT) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Wed, 2 Oct 2002 09:55:35 -0700 X-Originating-Ip: [207.202.171.254] From: "Mr. FoRK" To: References: Subject: Re: ActiveBuddy MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-Msmail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.50.4133.2400 X-Mimeole: Produced By Microsoft MimeOLE V5.50.4133.2400 Message-Id: X-Originalarrivaltime: 02 Oct 2002 16:55:35.0610 (UTC) FILETIME=[870831A0:01C26A34] Sender: fork-admin@xent.com Errors-To: fork-admin@xent.com X-Beenthere: fork@example.com X-Mailman-Version: 2.0.11 Precedence: bulk List-Help: List-Post: List-Subscribe: , List-Id: Friends of Rohit Khare List-Unsubscribe: , List-Archive: Date: Wed, 2 Oct 2002 10:00:48 -0700 X-Spam-Status: No, hits=-23.3 required=5.0 tests=AWL,CLICK_BELOW,KNOWN_MAILING_LIST,QUOTED_EMAIL_TEXT, REFERENCES,T_OUTLOOK_REPLY,T_QUOTE_TWICE_1 version=2.50-cvs X-Spam-Level: ----- Original Message ----- From: "Gary Lawrence Murphy" > ... and the one thing I think we've learned in all that time is that, > as a help-desk, it doesn't work. I'm not sure they are doing strictly help-desk stuff. But the whole 'who in their right mind would use that? it doesn't have all these cool features!' isn't always a guarantee of failure - maybe there is a strength in this approach (agents and/or IM as ui) than can find a nich application space. > > In all the prolog-based NL database query systems of the 1980's and > other later chatterbot helpdesk projects like Shallow Red, even > simpler tries like Ask Jeeves, people very quickly know they're > talking to a robot, and the queries anneal to short, truncated and > terse database-like verb-noun or just noun-keyword requests. Kind of like a web query - and with google, someone else can turn them into a link so you don't even have to type anything. > > People are just too quick to adapt, and too impatient to forgive a > clunky interface, and for now, especially when the /average/ computer > user still can't type more than maybe 5-10wpm, NL is a painfully slow > clunky interface. Yes - true true. > > Put it this way: Would you login, wake the bot and ask for the Seattle > weather, or would you do as we /all/ do and just click the weather > icon sitting there on your desktop? What about a situation where you don't directly ask/talk to the bot, but they listen in and advise/correct/interject/etc? example: two people discussing trips, etc. may trigger a weather bot to mention what the forecast says - without directly being asked.