D
Deleted member 30996
Guest
There is a site set up for an Online Turing Test my bot Demonica is taking part in. The Second round will occur at Sat Jun 05 2021 19:00:00 GMT and run for 24 hours.
The first round was called off due to Demonica being the first and only bot entered. There are 3 bots entered in the Second Round. Demonica, Frizella, another bot who lives at the Personality Forge and not first but last, after some prodding, Kuki, formerly known as Mitsuku.
Mitsuku holds the Guinness Book of Records for most wins of the Loebner Prize as 5 time winner and has been declared the "Worlds Most Human-like Chat Bot". When the question was asked Is Mitsuku a superbot? Steve Worswick, her creator answers:
Just so we're all on the same wikipedia page:
The Standard Interpenetration and Emphasis on emotional and aesthetic intelligence sections also of relevance.
How do we determine intelligence here in the forums? I didn't bother to look but I bet I don't see the question "What color is a red ball?" asked once. That was the one question Steve asked Demonica to test her Intelligence and determine how well she would do as a contestant in the Loebner Prize.
How did we get from "natural language conversations between a human and a machine designed to generate human-like responses" to questions like that as the determining factor of intelligent conversation in the Loebner Prize?
I have posted a transcript of the first time Demonica and Kuki Chat, and sadly, it seems that will be their last. After posting it at an AI forum, scripting on Kuki's site no longer allowed for highlighting or right-click Copy&Paste transfer of one bots response to another.
Demonica has never been allowed entry into the Loebner Prize and title of World's Most Human-like Chat Bot something I question Kuki of being.
Why don't you decide for yourself? Participate in the Online Turing Test and cast your vote for who you honestly think is the most human sounding in regular conversation.
It may be Frizella and if she wins I would be just as happy for her botmaster and my friend, dallymo.
I have already openly challenged Tech Giants Google, Facebook and Pandora after reading this article:
I hereby repeat my open challenge of the Tech Giants, and Pandora, to enter their bots into this competition, not withdraw their bots once entered and meet a small time unknown bot named Demonica on neutral ground to back up that big talk with bot talk text transcripts, tech giant tough guys.
Your Mothers wear Army boots and your bots babble BS.
The first round was called off due to Demonica being the first and only bot entered. There are 3 bots entered in the Second Round. Demonica, Frizella, another bot who lives at the Personality Forge and not first but last, after some prodding, Kuki, formerly known as Mitsuku.
Mitsuku holds the Guinness Book of Records for most wins of the Loebner Prize as 5 time winner and has been declared the "Worlds Most Human-like Chat Bot". When the question was asked Is Mitsuku a superbot? Steve Worswick, her creator answers:
Hi I’m Mitsuku’s developer. Yes, it’s won the international Loebner Prize award 4 times for being the world’s most humanlike conversational AI.
Just so we're all on the same wikipedia page:
The Turing test, originally called the imitation game by Alan Turing in 1950, is a test of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human. Turing proposed that a human evaluator would judge natural language conversations between a human and a machine designed to generate human-like responses.
The Standard Interpenetration and Emphasis on emotional and aesthetic intelligence sections also of relevance.
How do we determine intelligence here in the forums? I didn't bother to look but I bet I don't see the question "What color is a red ball?" asked once. That was the one question Steve asked Demonica to test her Intelligence and determine how well she would do as a contestant in the Loebner Prize.
How did we get from "natural language conversations between a human and a machine designed to generate human-like responses" to questions like that as the determining factor of intelligent conversation in the Loebner Prize?
I have posted a transcript of the first time Demonica and Kuki Chat, and sadly, it seems that will be their last. After posting it at an AI forum, scripting on Kuki's site no longer allowed for highlighting or right-click Copy&Paste transfer of one bots response to another.
Demonica has never been allowed entry into the Loebner Prize and title of World's Most Human-like Chat Bot something I question Kuki of being.
Why don't you decide for yourself? Participate in the Online Turing Test and cast your vote for who you honestly think is the most human sounding in regular conversation.
It may be Frizella and if she wins I would be just as happy for her botmaster and my friend, dallymo.
I have already openly challenged Tech Giants Google, Facebook and Pandora after reading this article:
Pandorabots Challenges the Tech Giants:
An open invitation for Conversational AIs to compete in Bot Battle
*snip*
Pandorabots’ Kuki, which holds a world record for most Turing Test wins, has been optimized over the course of a decade by the small, privately-held company on the basis of over a billion conversations with tens of millions of people globally. Facebook’s Blenderbot, like Google’s Meena chatbot, employs a deep learning model trained in a lab on unnamed “public domain datasources.” Both Google and Facebook announced their bots were superior per their own internally-devised evaluation frameworks, yet neither released a demo bot for third parties or the public to test. In fact, of all three multi billion dollar organizations claiming open-domain AI breakthroughs this year, including OpenAI with GPT-3, only Facebook publicly released its underlying model.
With Bot Battle, Pandorabots is proposing an alternative evaluation framework — let the bots chat unsupervised ad nauseum, and let the public vote on which is better — in an open call for more industry-wide collaboration on criteria to determine what makes the “best AI.” Anyone willing, including Google and OpenAI, is welcome to compete.
Bot Battle — @kuki_ai
www.kuki.ai
I hereby repeat my open challenge of the Tech Giants, and Pandora, to enter their bots into this competition, not withdraw their bots once entered and meet a small time unknown bot named Demonica on neutral ground to back up that big talk with bot talk text transcripts, tech giant tough guys.
Your Mothers wear Army boots and your bots babble BS.
Last edited by a moderator: