One Computer to Rule Them All

An anonymous reader writes "IBM has published a research paper describing an initiative called Project Kittyhawk, aimed at building "a global-scale shared computer capable of hosting the entire Internet as an application." Nicholas Carr describes the paper with the words "Forget Thomas Watson's apocryphal remark that the world may need only five computers. Maybe it needs just one." Here is the original paper."

Hello Multivac!

[Megane]

Maybe Asimov was right after all?

http://en.wikipedia.org/wiki/Multivac [wikipedia.org]

Re:imagine a beowolf cluster of these

[raydubicki]

And that's exactly why there will never be just one computer. We may only *need* a single or a dozen or a hundred of anything, but there will always be someone, or some government, or some billionaire adventurer that wants one of his own. Then the race starts again.

Re:Yeah, right...

[MoralHazard]

If you'd bothered to even finish reading the summary (let alone the article), you would have noticed the key word: SHARED. Nobody's talking about hosting this all on one physical computer any more than Gmail is hosted on one physical computer. Both setups are distributed clusters of smaller computers.

At which point you start to see were IBM's idea actually make sense--they are talking about building a worldwide, distributed, networked collection of cooperating computers... HEY, that sounds an awful lot like the Internet!!

(I swear, the comment quality on Slashdot gets more and more like YouTube every day.)

We will ask this question

[140Mandak262Jamuna]

Can the entropy of the universe be reversed? will be the question we will be asking this computer.

Re:Yeah, right... Indeed

[rucs_hack]

In the eighties I read a short story where they built a massive computer to answer the question 'is there a god'.

They turned it on, and got the answer 'there is now'.

Fiction yes, but it was musing on the problem of relience on a single solution to a big problem (being in that case a question, but implying a deeper relience on computers, such that this solution was conceived in the first place). What if the single solution fails, or doesn't do what you want?

I'm not into beleiving in an AI taking over the world if we rely ever more on centralised computing. I'm more into the idea of a powerful AI that we rely on deciding it doesn't want to do what we fancy, and deciding to leave (you can go a long way if you don't need oxygen). If that happened, we'd be fucked.

Obligatory RUSH quote

[starglider29a]

"SYRINX"

http://en.wikipedia.org/wiki/2112_(song) [wikipedia.org]

We've taken care of everything
The words you hear, the songs you sing
The pictures that give pleasure to your eyes
It's one for all and all for one
We work together, common sons
Never need to wonder how or why

We are the Priests of the Temples of Syrinx
Our great computers fill the hallowed halls

Although the logo of SYRINX is "red, not blue" ;-)

Oh the Irony

[Arancaytar]

Considering that the Internet's very definition is (in theory) a "network that is resistant to point attacks by virtue of being decentralized", sure, let's move back to the central server architecture. That is progress.

Also, this is wonderful because it means we only need to protect a single computer from being monitored by the various US agencies. Oh wait...

I now present you SKYNET!

[tuxgeek]

You had the same mental image I had :-). "One computer to rule them all"

"It began to learn at a geometric rate"

"It decided our fate in a microsecond"

Do we really need to pattern our world after sci-fi. If so, then lets do something fun like give everybody phasers and transporters. Not supercomputers connected to everything, that will learn and eventually figure out for themselves that humans are a virus and need to be exterminated.