Remember a few years ago I was looking for a TANU Bot? Well even though the bot could not be found by any of my friends of associates, I did happen across this excerpt today by means of an archival service. This is going back to 2003-4 but I thought it showed a lot of potential for the time.
This should serve to wet your appetite! or is that whet?
T.A.N.U. - With the TANU (Transplantable Artificial Neurological Units) architecture you can create, train and deploy your AI chatbot to ANY IRC or non-IRC chat network. That means ANYWERE you chat you can bring your TANU chatbot.
Your bot's are as smart as you train them to be and you can bring them anywhere you chat. Or chat with one solo using this open source application. TANU is an archtecture with a service for hosting AI chatbots. You are welcome to modify this application to bind your TANU chatbot to your favorite place to chat. You can chat w/ other people's chatbots by visiting our IRC network: irc://irc.chatbot.us[^] (will need an IRC client like the latest mIRC installed
http://www.mirc.com/get.html[^] ) or by finding TANU compliant bots in chat rooms all over the web. Once on the network /join #tanu or /join #ai or /list for a list of all chat rooms. irc://irc.chatbot.us[^] dedicated to AI and full of AI chatbots, trainers, AI discussion, etc. Not all of the chatbots on irc://irc.chatbot.us[^] are TANU but most are as TANU bots can be easly transplanted into a neptune chat room w/ the built in TANU Stork services here is a tutorial on that:
http://www.p2bconsortium.com/stork.html[^] If you chat alot, chances are you have already conversed with a TANU (Transplantable Artificial Neurological Units) chatbot. If you follow this tutorial you can create your own TANU bot to chat with.
http://www.p2bconsortium.com/ online trainer's library has more info on this. Feel free to stop by our network anytime irc://irc.chatbot.us[^] ( chatting in irc.chatbot.us requires an IRC client like the latest mIRC[^] installed )
The TANU Philosophy – Billy punches Joe in the arm
AI chatbot architectures prior to TANU (Transplantable Artificial Neurological Units)
start out semi-smart and grow less intelligent as they pick up information from human
chatters. Particularly, when humans deliberately speak garbage to AI chatbots. This is not
altogether the human’s fault, humans often speak meaningless sounds to babies such as
“peek-o-booo†or “googoo-gaagaa†etc. The human babies don’t grow stupid from it. Why?
Because human minds are not all environment, rather DNA. In one abstraction, we are all
products of our DNA and our environment has no effect on us. For example, Billy punches Joe
in the arm “making Joe tougher†could be abstracted as Billy’s bully genetics that he inherited
from his ancestors merged with Joe’s malleability that he inherited form his ancestors. Why
not skip the whole growing up and letting Billy punch Joe in the arm? The TANU philosophy
proves that the new post-punched Joe personality can be obtained by merging Billy’s
genetics with Joe’s genetics.
( These sections from Person 2 Bot Standards Online Library
http://www.p2bconsortium.com/ )
Does this mean that the post-punched Joe is the result of merging Joe and Billy’s
personalities?
Yes. However, the pool of genetic maps that make our state of mind at any point in time is a
much larger set of inputs, the genetic codes for billions of living things effect who we are at
any given point in time.
Then how to create AI since computers don’t have billions of megabytes required to
model the genetics of all relevant life?
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.
70,000 interconnected states is still to much work
If you and 9 friends create an link (via transitions) about 100 states an hour Monday-Friday
for about 2 weeks you will have a collective of 72,000 states. The trick 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 child hood
and go through the years linking and adding states to the collective.
But how can all 10 of us work concurrently?
The TANU servers have advanced multi-user capabilities. Simply create one TANU chatbot
with this open source tool and share the password and bot name with your 10 other trainers.
Or you can modify this code and create your own custom interface into the TANU
architecture and distribute your own TANU tool 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.
What is a TANU sentinel?
TANU sentinels are processes that run on the TANU servers and monitor all TANU chatbots
for corrupt data, garbage data, and administer corrective actions. If a state name is to
short or common a sentinel is likely to reject it. So, although you need to create your states
quickly, make sure the state names are large enough to have a good chance of being unique.
