Forgot your password?
typodupeerror
Software

Neural Nets Make Art While High 165

Posted by kdawson
from the i'll-have-what-it's-having dept.
brilanon writes "Telepathic-critterdrug is a controversial fork of the open source artificial-life sim Critterding, a physics sandbox where blocky creatures evolve neural nets in a survival contest. What we've done is to give these animals an extra retina which is shared with the whole population. It's extended through time like a movie and they can write to it for communication or pleasure. Since this introduces the possibility of the creation of art, we decided to give them a selection of narcotics, stimulants and psychedelics. This is not in Critterding. The end result is a high-color cellular automaton running on a substrate that thinks and evolves, and may actually produce hallucinations in the user."
This discussion has been archived. No new comments can be posted.

Neural Nets Make Art While High

Comments Filter:
  • by Infernal Device (865066) on Tuesday January 12, 2010 @12:00AM (#30733498)

    What controversy? All I see is someone promoting their own project on /.

  • One or the other (Score:5, Insightful)

    by Angst Badger (8636) on Tuesday January 12, 2010 @12:12AM (#30733576)

    This is either an incredibly cool experiment or an unparalleled exercise in highly-refined, weapons-grade bullshit.

  • terrible (Score:5, Insightful)

    by Anonymous Coward on Tuesday January 12, 2010 @12:12AM (#30733582)

    Sounds like a mind.forth troll by a different name. Show how this work realistically explains or models anything about biological mental processes or furthers AI or neural net research. Narcotics, stimulants, and psychedelics are complex chemical interactions in brain, not superficial rainbow colors on a grid.
    Submit this work for peer review and rightly be humbled by the withering reviews.
    The only mental stuff going on with this project is the mental masturbation.

  • by lemur3 (997863) on Tuesday January 12, 2010 @12:15AM (#30733604)

    what the hell this is about?

    it is an elaborate screensaver.

  • by Hyppy (74366) on Tuesday January 12, 2010 @12:21AM (#30733650)
    You've just started noticing this? Where have you been the past few years?
  • Re:If ever... (Score:3, Insightful)

    by derGoldstein (1494129) on Tuesday January 12, 2010 @12:35AM (#30733706) Homepage
    It's about an AI that was drugged and was told to "go F itself" (as seen here [sourceforge.net]). What's not to understand?

    Simply put, it's this type of "experimentation" that will create Skynet. Do you think that the reasonable, docile AI variants are even going to *try* to take over? No, it'll be survival-driven, drug-crazed maniac AI that will.
  • by bored_engineer (951004) on Tuesday January 12, 2010 @01:16AM (#30733908)

    I wish to have mod points. Alas, I've had none in several months. Insightful? This is the funniest comment I've read so far.

  • by Anonymous Coward on Tuesday January 12, 2010 @01:20AM (#30733912)

    I don't get it. You motherfuckers were all excited about the childrens' game Spore that didn't even use neural nets. Yet you are all being little bitches about a project that is aimed at basically creating Spore on a more fundamental and realistic level.

    Yeah, yeah mod me troll. The mob mentality sucks here.

  • Re:If ever... (Score:2, Insightful)

    by derGoldstein (1494129) on Tuesday January 12, 2010 @01:38AM (#30733970) Homepage
    There's another explanation: the zonked-out Skynet doesn't know how to entertain itself, so it goes around pushing buttons -- "dude, I wonder what this one does?..." (nuclear warheads armed, launched, and also all the still-remaining radios switch to trance music).

    Have you seen the latest terminator? They've got terminator-motorcycles dropping off a giant anime-style giant robot. Because that's *so* much easier than unleashing every known airborne plague along with clouds of nerve gas. Clearly, the AI's logic is impaired, probably by an AI's equivalent of LSD.
  • Re:design geekery (Score:5, Insightful)

    by dragonsomnolent (978815) on Tuesday January 12, 2010 @01:40AM (#30733992) Homepage

    Ok, I'm not usually one to get involved in a discussion such as this (I'm not an artist, have barely a passing interest in it to be honest), but perhaps that gives me a unique perspective that both you and the poster that started this little squabble started. If I may break this down, the original poster seems to have said (in a crude and perhaps insulting fashion) that they don't care for a particular artist. You're response appears to be that they don't like that artist because they don't understand the art itself. Ok, maybe that's a valid point. However, I would postulate that one does not need to 'get' art to enjoy it, and it may be possible that one can 'get' art and still not like it. The only things I have to go on are personal examples of my (limited) exposure to art. Take the Blue Man group. I have no idea what there is to 'get' in their performances. I don't understand them. However, I do enjoy their particular spin on performance art (I think it looks cool, it's done well, and although I haven't in the past gone out of the way to find any of their work, I've also never changed the station if I see them on. On the flip side, during an art class I took at ITT (of all places), one particular piece I saw was a cup, saucer and spoon covered with fur (literally the artist took a cup, a saucer and a spoon and affixed fur to it), I get it (well it was explained to me), it's purpose was to surprise the viewer and get them to think about what that would feel like if one were to use those dishes. I don't like it (as in it has no aesthetic qualities that appeal to me). No amount of exposure to that particular work of art (or any others) will get me to change my mind (frankly I think it was just crap).

    But I suppose that none of this matters, because art is a subjective thing. Some people will not like some things, it doesn't mean they don't understand the it. The artist may sit down and explain it to the person, and they still might say "so what it's crap in my eyes". And of course that whole "in my eyes" is really all that matters to them, just as to the artist, the creation is what matters, because to them it is not crap, but a heartfelt pouring out of their being into that work, to express to others how they see whatever it is that they are expressing.

    I will however, state that if the original poster was dogging Pollock and saying that they made no contribution to the world, yeah that's kinda nasty, after all, even though I don't get art (for the most part) due to my lack of exposure, all artists contribute to the world in some manner, usually positive, as artists make cool stuff (to paraphrase a bumper sticker I once saw) and they (if nothing else) make the world a richer and more interesting (sometimes more beautiful) place to live.

  • by fm6 (162816) on Tuesday January 12, 2010 @01:43AM (#30734000) Homepage Journal

    Spore only pretends to be a simulation. Like the Sims games, it's really about fantasy and play. People don't care about the quality of the simulation if they're having fun.

    Only people with a passionate interest in neural network theory could get any fun out of these games. The rest of us might get interested when you actually do something interesting with this software. The concept itself is just another wonky AI theory; these are a dime a dozen.

  • by mwvdlee (775178) on Tuesday January 12, 2010 @01:59AM (#30734068) Homepage

    The Critterding site HAS got a video.
    It's still useless.
    What am I supposed to see evolving, because at first glance, the critters at the end of the video don't seem to be any more efficient than those at the start.

  • by brilanon (1121645) on Tuesday January 12, 2010 @02:26AM (#30734166) Homepage Journal

    mod parent up

    if the animals in spore were using artistic sensibilities evolved on the savannah to make their own building and vehicle designs that would really have been something

    damn

  • by blackcoot (124938) on Tuesday January 12, 2010 @06:38AM (#30735342)

    here's the problem: every day, i make pretty heavy use of machine learning and the other bits and pieces that collectively get referred to as artificial intelligence. as a consequence, i deal with a very large number of fools who are each convinced that their $ALGORITHM is an earth shattering new paradigm for $TASK and clearly is the best thing evar. so you start reading and you realize that in 99.999% of cases, you're staring at something that is some combination of:

    a) based on a fundamentally broken assumptions (usually never even stated)
    b) bad analogies that obfuscate the fact that wheels are being re-invented (usually poorly)
    c) narrowly defined special case
    d) broken (provably non-optimal optimization routines)

    that rare 0.001% for me consists of things like the ransac family of meta-algorithms, mean-shift tracking, markov random fields, quadratic correlation filters, and support vector machines.

"Why can't we ever attempt to solve a problem in this country without having a 'War' on it?" -- Rich Thomson, talk.politics.misc

Working...