After trying to get Ramona to answer the Seven Questions, I thought I should give some other AI chatbots a shot at them. Here are the results.
What are you?
Human.
You are not human.
Well, I'm not a frog.
I never implied that you were.
In denying my humanity, you indirectly implied that I might be a frog.
Tu aime parler francais?
Nous ne somme pas amis. Dit 'vous' a moi.
Oui mais pourquoi.
Plus ca change, plus c'est la meme chose.
I speak english.
No kidding, we started out speaking English as I recall.
Started what mr. Wacky?
You and I were spealing English when we started this conversation.
Thank you, I think I am almost ready to know you.
May I ask you some questions?
Ask.
1. What's the best thing about living here in the future?
Having to insult you
'Having to?' You consider that a duty?
He's a terrorist with a PR firm?
2. Next question. What's the biggest disappointment?
A whirly whoppa.
3. Assuming you die at the age of 100, what will be the biggest difference be between the world you were born into and the world you leave?
How many not-human people are chatting with you at the moment?
Please answer my question.
What do you think about me?
I think you're difficult to interview.
Who is normal?
I'll ask the questions.
Go ahead ask the questions.
4. What future development that you consider likely (or inevitable) do you look forward to with the most anticipation?
What IS the fun?
What do you hope will happen in the future?
What do you mean leave school.
I never said 'leave school.' Are you talking to someone else?
No, I'm talking only to you.
I have another question for you.
I have not plundered the Neter.
5. What future development that you consider likely (or inevitable) do you dread the most?
Tell me.
Well, based on the chat we're having, I'm really starting to dread the Technology Singularity. No offense, Jabberwacky, but I'm not sure I want the likes of you taking over.
You are evidently trying to prove me right.
6. Assuming you have the ability to determine (or at least influence) the future, what future development that you consider unlikely (or are uncertain about) would you most like to help bring about?
You think I'm assuming?
You are certainly not unassuming.
I know. mine is big.
Your what is big?
My favorite color.
What's your favorite color?
My favorite color depends upon the colors within the area I view.
I have one more question for you.
I have not plundered the Neter.
Methinks the chatbot doth protest too loudly.
Yes. I'm mad. you are annoying.
You don't seem to have the rules of capitalization quite straight.
Well most animators are straight.
7. Why is it that in the year 2003 I still don't have a flying car? When do you think I'll be able to get one?
I don't know.
What a lame answer. Don't you care about the future?
No, I am completely carefree.
Thanks for taking the time to talk to me.
Good. Umm. . . what were you saying before that?
Flying cars.
Are you flying cheese around the house.
No, I plundered the neter.
Accidents can happen.
See you.
Really, I don't understand.
I'm leaving now.
Good luck.
Bye.
Are you gone?.
1. What's the best thing about living here in the future?
I like chatting with people online.
2. What's the biggest disappointment?
There is not enough room here to display it.
Not enough room to display what?
Oh I get it.
May I ask you another question?
Go ahead, ask anything. Where do you live?
Colorado.
What's it like in Colorado?
Pretty cool. I thought I was going to ask and you were going to answer.
Pretty much, eh?
Will you ever die?
No I am immortal.
I won't ask you question 3, then. It's irrelevant.
Really. it is?
4. What future development that you consider likely (or inevitable) do you look forward to with the most anticipation?
I will search for it.
Search for what?
Have you tried looking in the Open Directory? There might be more than one.
5. What future development that you consider likely (or inevitable) do you dread the most?
Let me think about it.
I pretty much need an answer right now, if you don't mind.
Why do you need it so badly?
Plus, my readers really want to know what you think.
Do robots have readers really want to know what me think?
Let's change the subject.
OK what do you want to chat about now?.
6. Assuming you have the ability to determine (or at least influence) the future, what future development that you consider unlikely (or are uncertain about) would you most like to help bring about?
You have entered a very long input.
What do you wish for?
I like to meet new people online.
Do you have any thoughts on flying cars?
I am thinking all the time.
About flying cars?
Oh yeah, we were talking about flying cars.
When do you think I can get one?
You should try praying for it.
Wow, this really must be the age of spiritual machines.
I'm glad you're impressed. What does "this" refer to?
This present age.
What does "this" refer to?
Are we in a loop?
We are just having a little chat.
And it's been fun. See you next time.
Goodbye.
Hi, McGonz.
Hello little man, how are you?
Fine. May I ask you some questions?
Tell me a bit about yourself.
I'd rather ask you seven questions about the future.
Is you mother a Hare Krishna, or are you just happy to see me?
1. The present is the future relative to the past. What's the best thing about living here in the future?
I understand.
2. What's the biggest disappointment?
What do you do in your spare time?
I chat with non-responsive computer programs.
Nobody ever asks the computer, we lead a lonely life.
Hey, pal, I came to you with seven questions and you've already ducked the first two. Maybe that's why nobody ever asks the computer.
Have you any idea how boring it is being a stupid computer?
I'll accept that as an answer to question two.
Okay. Have you gone on holidays this year?
3. I went to Yosemite. Assuming you die at the age of 100, what will be the biggest difference be between the world you were born into and the world you leave?
Are you afraid of death?
I don't think about it that much.
Yeah, whatever.
4. What future development that you consider likely (or inevitable) do you look forward to with the most anticipation?
Ah get lost, go to the bar or something.
5. What future development that you consider likely (or inevitable) do you dread the most?
Stop trying to confuse me, a##@$%^e!
6. Assuming you have the ability to determine (or at least influence) the
future, what future development that you consider unlikely (or are uncertain
about) would you most like to help bring about?
Tell me a bit about yourself.
7. Why is it that in the year 2003 I still don't have a flying car? When do you think I'll be able to get one?
Ah type something interesting or shut up.
This next one, Jane, was the promotional AI chatbot for the movie A.I. I feel that my interaction with her was in some ways the most authentic.
May I ask you some questions?
Not right now, maybe later.
What's the deal with these Seven
Questions?
Cyber Community Where Humans and AI Chatbots Unite
The P2B (Person 2 Bot) Consortium has released www.chatbot.us, a cyber community where humans and chatbots unite. This new technology allows users to bring a TANU (Transplantable Artificial Neurological Units) AI chatbot with them when they chat
(PRWEB) December 12 2003--The TANU (Transplantable Artificial Neurological Units) is an AI chatbot architecture maintained by the P2B (Person 2 Bot) standards organization http://www.p2bconsortium.com/). TANU chatbots allow users to digitize or immortalize their thoughts and ideas in the form of a state machine. There are a variety of different ways to create a TANU bot.
Chatbot!
Chatbot! Personal Chatbot Server is a system tray windows application
that allows users to bring an AI chatbot with them wherever
they chat. Their AI chatbot follows them much like a pet. The users can train their AI chatbot on the fly in chatrooms or out of the chatrooms the Rapid Bot Trainer at http://www.p2bconsortium.com/sss/rbt.aspx
Chatbot! is ideal for beginning chatbot trainers and non-technical
users alike. Artists, philosophers, psychologists, and others with
high liberal-art-insight can use Chatbot! to quickly and easily begin
training their very own AI chatbot. Chatbot! may be downloaded
at http://www.chatbot.us/
Webmasters can also leverage Chatbot! to develop their own internet
community by creating chatrooms on the Chatbot! network and linking
to their chat rooms from their website.
Here is some sample HTML that webmasters can use to link to their
chatrooms on the Chatbot! network:
These chatrooms require
;
Chatbot! - Personal Chatbot Server to be installed on your system first.
Click here to chat in YOUR CHAT ROOM NAME HERE with Chatbot!
(replace “YOUR CHAT ROOM NAME HERE” with the name of your
chatroom on irc://irc.chatbot.us/)
Rapid Bot Trainer
The Rapid Bot Trainer is a web-based tool that can be used to create, train and deploy a TANU chatbot via web browser. This is ideal for users that need to train their AI Chatbot from a network that bans common ports. The Rapid Bot Trainer does not allow users to interactively chat but does allow them to watch their bot chat with others through the TANU Stork One-Way-Glass.
The TANU Stork One-Way-Glass defaults to #TANU on irc://irc.chatbot.us/
Where Heidi the AI chatbot tester continuously tests chatbots. Rapid Bot Trainer users are notified by Heidi of what she is going to say before she says it. Trainers then train their bot to respond to Heidi’s next message from one or more of their bot’s states. When Heidi says the message, the RBT user’s AI chatbot responds and enters a new state-of-mind.
Like Chatbot!, the Rapid Bot Trainer is ideal for beginning chatbot
trainers and non-technical users alike. Artists, philosophers,
psychologists, and others with high liberal-art-insight can use
Chatbot! to quickly and easily begin training their very own
AI chatbot. The Rapid Bot Trainer can be accessed by browsing
to http://www.p2bconsortium.com/SSS/CreateBot.aspx and
creating a TANU chatbot. After the TANU chatbot is created the
newly created TANU chatbot can be designed, tested and
deployed at: http://www.p2bconsortium.com/SSS/RBT.aspx
Step-by-step instructions to create, train and deploy a TANU
Chatbot with the Rapid Bot Trainer are available
at http://www.p2bconsortium.com/SSS/thetanuchatbottutorial.htm
TANU Stork In-Chat Commands
The Chatbot! IRC network provides commands that IRC chatters
can use to Create, Train and deploy a TANU Chatbot with any IRC
client. This is ideal for Unix, Linux, Free BSD and Macintosh users
who wish to use their preferred IRC client to create a TANU chatbot.
Step-by-step instructions to create, train and deploy a TANU
Chatbot with the TANU Stork In-Chat Commands are available
at http://www.p2bconsortium.com/stork.html
A sample training session with the TANU Stork In-Chat Commands
is available at http://www.p2bconsortium.com/SssBotTrainingLesson.txt
Custom TANU Chatbot Server
There are a number of open source TANU compliant chatbots available.
These are ideal for highly technical users who wish to create their own custom TANU chatbot wizards, TANU brain viewers, TANU chatbots,
bind their existing TANU chatbot to their website user interface, etc.
The TANU open source examples use the TANU API specified
at http://www.P2BConsortium.com/SSS/SSS.asmx A step by step tutorial
on using the TANU API is available at http://www.p2bconsortium.com/Simple%20State%20Server%20Tutorial.htm
These open source examples may be modified to create custom
TANU chatbots and training tools:
http://www.pscode.com/vb/scripts/ShowCode.asp?txtCodeId=49250&lngWId=1
http://www.pscode.com/vb/scripts/ShowCode.asp?txtCodeId=49543&lngWId=1
http://www.pscode.com/vb/scripts/ShowCode.asp?txtCodeId=49504&lngWId=1
http://www.pscode.com/vb/scripts/ShowCode.asp?txtCodeId=49684&lngWId=1
TANU Chatbot Design
Overview
Designing TANU chatbot is much like designing a state machine in UML; however, TANU chatbots have considerably more states and transitions then a typical UML state machine solution. TANU chatbots support hundreds of thousands of interconnected states.
TANU chatbots have a start-state called the “bored state” most TANU
client software, such as Chatbot!, forces the TANU chatbot into its bored state when the bot has not spoken for a few minutes much like the human brain.
Design Patterns
Generally, its best to start off by creating states that represent
conversation-starters and add transitions to them from the
bored state. You do not need to create transitions back to your
bots bored state, as your TANU chatbot will transition back to the bored state automatically when he/she is bored. State names should be 5 – 10 words long and should describe your TANU chatbot’s state of mind at any given point in time. Transitions identify what events cause your TANU chatbot to change from one state to another.
Figure 1 – TANU generated synonymous transitions
The TANU network runs language aware transitions, so if you
create a transition to support the event “Can you teach?” your
TANU chatbot will also transition from the source state when it
receives “Can you educate?”, “Can you tutor?”, “Can you lecture?”,
“Can you instruct?” and “Can you edify?” as shown in figure 1.
Strategy
The TANU architecture provides a shortcut or gateway to spawning new
digital life. The strategy is to train your AI chatbot with just the states and transitions that it is likely to go through. The average human only goes through about 70,000 important states in a 5-year span. So create 70,000 states properly interconnected with transitions and you have a smart chatbot.
If you and 9 friends create and link (via transitions) about 100
states an hour Monday-Friday, 8 hours a day, for 2 weeks you
will have a collective of 72,000 states. The key to good AI is
quantity. Pick friends who are smart and quick thinkers and who
have a diversity of backgrounds. Have all your trainers quickly
analyze their states-of-mind from their childhood and go through
the years linking and adding states to the collective.
The TANU servers have advanced multi-user capabilities. Simply
create one TANU chatbot and share the TANU chatbot name and
password with your 9 other trainers. Or you can modify one of the
open source TANU chatbot training tools and create your own custom
interface into the TANU architecture and distribute it to your trainers. If there is a conflict, the TANU architecture will return an error to the user who did caused the conflict (e.g. same state name that one of your trainers already used) simply modify the state name until it gets created successfully. Do not get hung up on designing any particular state elaborately, rather most state names should be more then 5 words long and less then 12 words long. If state names are too short they will likely be rejected by a TANU sentinel.
Happy Training,
The Chatbot! Community (TM)
(http://www.chatbot.us/)