[goaty]

Hi.   

Id love to see the day where we have a new kind of animal, controlled by a powerful computer, the whole idea is oozing with pleasure, when is someone going to get off their butt and show me that a computer can actually communicate!

[goaty]

Heres my latest project, I don't work very quickly because I have bad energy problems, I cant even type 2 keys some days,  but here ive got a folding starfish project (You repeat rotate it 4 times in a circle to make the finished bot.)  The legs move,   but its just an outer exoskeleton, It needs to have muscles inside it.

there is tonnes of errors in this, I need to go over it tomorrow, and some of the lines are the wrong angle, and theres a few triangles missing but its close.  I ended up screwing it up before I could get the screenshot a bit sorry.

Theres this really clever way to animate robots that comes from a long time ago,  the automatons used to run off one turning engine, and cogs hit the cogs and it ends up coming out the creatures legs, in different animation settes.

I think I want to try pully cables like bicycle breaks to get up into the leg, I think the knee and wrist bends could take more nerves down from above by Rolling on pulley supports, to be kind to the pully cables.

If there is a way easier than pully cables I doubt it,  I thought about it a-long time.....

[Korrelan]

Welcome Goaty

 

[HS]

Welcomes!
Nice project. I do love steampunk. I would also love to build a robot in that style.

[Art]

Hello Goaty! Welcome aboard!

[AndyGoode]

Welcome to the forum, Goaty. I'm pretty new here myself.
One tip about your thinking: Don't assume that AGI must be powered by a "computer." It might be powered by a neural network, cellular automaton, or some other exotic type of machine.

(p. 12)
   It was like running into a brick wall. MIT was the mother-
ship of artificial intelligence. At the time I applied to MIT, it was
home to dozens of bright young people who were enthralled with the
idea of programming computers to produce intelligent behav-
ior. To these scientists, vision, language, robotics, and mathe-
matics were just programming problems. Computers could do
anything a brain could do, and more, so why constrain your
thinking to biological messiness of nature's computer?
Studying brains would limit your thinking. They believed it
was better to study the ultimate limits of computation as best
expressed by digital computers. Their holy grail was to write
computer programs that would first match and then surpass
human abilities. They took an ends-justify-the-means approach;
they were not interested in how real brains worked. Some took
pride in ignoring neurobiology.
   This struck me as precisely the wrong way to tackle the
problem. Intuitively I felt that the artificial intelligence approach
would not only fail to create programs that do what humans can
do, it would not teach us what intelligence is. Computers and
brains are built on completely different principles. One is pro-
grammed, one is self-learning. One has to be perfect to work at
all, one is naturally flexible and tolerant of failures. One has
a central processor, one has no centralized control. The list of dif-
ferences goes on and on. The biggest reason I thought comput-
ers would not be intelligent is that I understood how computers
worked, down to the level of the transistor physics, and this
knowledge gave me a strong intuitive sense that brains and
computers were fundamentally different. I couldn't prove it,
but I knew it as much as one can intuitively know anything.
(p. 13)
Ultimately, I reasoned, AI might lead to useful products, but it
wasn't going to build truly intelligent machines.

Hawkins, Jeff. 2004. On Intelligence. New York: Times Books.

[goaty]

Welcome to the forum, Goaty. I'm pretty new here myself.
One tip about your thinking: Don't assume that AGI must be powered by a "computer." It might be powered by a neural network, cellular automaton, or some other exotic type of machine.

Yes I know, for example If I were to go make a.i. hardware,  the best thing I can think of is something like a ram chip, that takes an input pattern, then matches the whole store at the same time and produces the nearest neighbour. 

That is a root optimization over an ordinary computer doing nearest neighbour!

[AndyGoode]

Everyone should also be aware that when thinking about any computing system, three different levels of a hierarchy exist. The bottom level is hardware, which is the least important. A computer or neural network could be built out of anything from silicon to Tinkertoys to human flesh and it would still be organized the same, other than physical material. The next level of abstraction is the algorithmic level, which is where the real mystery of AGI lies: how is the information stored, and what is being done with that representation? The top level we already know, which is basically the goal.