Invitation for the Greatest Project

Started by
48 comments, last by saintdark 19 years, 5 months ago
Hello all, I would like alll the people over here interested in AI to come and join the Nex Project. Check out the details at www.geocities.com/project_nex I've had enough of criticism regarding AI, the grammar mistakes..Plz ignore these things if you see them Regards Saint Dark
Advertisement
For the lazy:

Quote:
Project NEX is an effort to build the ultimate intelligent standalone Operating system. Nex will be a completely independent intelligent entity with the ability to self evolve its code, except its primary objectives. This project is in its early stage of planning, the developing part will commence on 1st jan 2005, the next year. Before that all the plans, approach, cycle and almost everything should be ready.


Wow, can I be a tester? ;)

This isn't a criticism, but let's hear your summary of why you think you can do this and what your resources are.

As for self-evolving its code, would this be useful? I can think of uses for an intelligent, pattern-recognising OS, but not one that evolves its own code.
"Learn as though you would never be able to master it,
hold it as though you would be in fear of losing it" - Confucius
grammer engine: ironic, huh
sorry, i just had to say it.
good luck anyhow
dont forget to put the four laws in there:

1) The OS may not injure a human being, or, through inaction, allow a human being to come to harm.
2) The OS must obey orders given it by human beings, except where such orders would conflict with the First Law.
3) The OS must protect its own existence as long as such protection does not conflict with the First or Second Law.
4) The OS must not delete pornography, nor through inaction, allow porn to be deleted.

otherwise we end up with skynet, and although they are cool i don't want to have to actually deal with terminators.
--- krez ([email="krez_AT_optonline_DOT_net"]krez_AT_optonline_DOT_net[/email])
Maybe in some virtual environment, I would look at it, but what stability is there? I mean, we can't even build a bot that can past the turing test, how are we suppose to build a full OS that can evolve code? I am not questioning the idea, which is great, but the ability to execute it?
What's used for KR? Is there a specific format? KIF? KMQL? OpenCyc? OpenMind? Custom?

I think it'd be neat. I can only imagine it being written in its own language though, or a combination of low-level traditional os components and high-level ai components(whatever design, the language itself should be designed to be evolved).
Quote:Original post by red_sodium
... As for self-evolving its code, would this be useful? I can think of uses for an intelligent, pattern-recognising OS, but not one that evolves its own code.

Off the top of my head, I can only think of code-efficiency. Obviously, one would like to have an OS that boots in 12 seconds, or starts up with all of your most used applications cached, ready to go. (Can you manipulate the code-evolution? ie, bias the OS for speed, versus robustness - or both?)
I would assume that an OS that can evolve could reasonably simulate any other OS as well - (VM or otherwise. This could lead to a Windows-based OS that actually works.)
Um ... I'm thinking about program-specific tuning as well. Having your entire OS evolve for a particular program each time sounds very interesting indeed.
Can't think of any others right now.
Thx guys
Got lotsa replies.. Thank you for posting...
--As for code efficiency, the OS will have to learn to make its code more efficient on its own..
The Operating system will decide over time wht to run and wht not to run.
THE PLAN IS NOT TO MAKE AN OS THAT IS INTELLIGENT IN CERTAIN AREAS.. IT HAS TO LEARN EVERYTHING OWN ITS OWN.. WE WILL JUST PROVIDE THE BASIC NECCESSARY DETAILS.. AND THE FIRST VERSION OF ITS CODE ;)
The methods of communicating is Graphics,Voice, Data[text].etc

--Yes a self evolving language has to be planned, combined with some low-level os langs.

--Dont see this as a project that is 100% realizationable.. It is a kinda research project guys.. stability will depend on how we do it. i cant do this alone i need help from nerds like u.. when lots of ppl think some idea will click.. And talking about bots not passing the turning test ..i dont know why. if we decide and make an effort, the test can be passed..

Its been one week iam running al over , smbdy, even a single person is yet to come, whtever im never gonna give it up..

YOU CAN REALLY MAKE A CHANGE.
Quote:Original post by saintdark
--Yes a self evolving language has to be planned, combined with some low-level os langs.

What about Lisp? I know that there are some Lisp OS's out there. Just hack in the GP capability as a test run of the possibility.

Anyway, this sounds pretty cool. What implementation details have you worked out so far?
If a plant cannot live according to its nature, it dies; so a man.
i just have this outer plan 'woods'. I need more volunteers to take decisions and sm brainstorming sessions...
R u interested in the project..
thought abt lisp.. but dunno much abt its stability with other low-level langs...
regards
saint dark

This topic is closed to new replies.

Advertisement