Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[wierd]

Dont get me started on the human fixation on "popularity" and positions of power. That's a road best not traveled.

However, given the inexorable nature of that problem, coupled with the democratic-republic nature of the US's electoral system, it is inevitable that presidential and congressional popularity indices will be useful metrics for gauging how the next election cycle will pan out.

Nobody ever said this kind of government was ideal. Far the contrary I believe. Just that it is one of the better options available.

Personally? I'd rather turn control of government over to a deep learning AI. Train it at the city level for awhile, then let it move up as it improves. At least the AI would make logical and rational choices.

[Graknorke]

Rational is terrifying though. Depending on what it's meant to be optimising logical can go some very bad ways.

[wierd]

Terrifying can be both good and bad.

Take for instance, tort reform. Terrifying.

[MonkeyHead]

Rational is terrifying though. Depending on what it's meant to be optimising logical can go some very bad ways.

Indeed. It would be not so surprising if an AI identified humans as the weak, irrational and inefficient link in global society. Eliminating us could end crime, world hunger, war, and so on...

How logical.

[wierd]

A deep learning AI of current state of the art would not be able to reach such a conclusion.

Instead, it would base its decisions on the metrics it has been programmed to analyze, and the outcomes of prior decisions, both made by itself and by human contemporaries.

It would be terrifying, because it would give us the government we deserve.

[Loud Whispers]

However, given the inexorable nature of that problem, coupled with the democratic-republic nature of the US's electoral system, it is inevitable that presidential and congressional popularity indices will be useful metrics for gauging how the next election cycle will pan out.

A worthless exercise because the choice is meaningless, both lead to the same outcome only diverging on whether they like homosex

Nobody ever said this kind of government was ideal. Far the contrary I believe. Just that it is one of the better options available.
Personally? I'd rather turn control of government over to a deep learning AI. Train it at the city level for awhile, then let it move up as it improves. At least the AI would make logical and rational choices.

We must dissent

[Graknorke]

Nobody ever said this kind of government was ideal. Far the contrary I believe. Just that it is one of the better options available.
Personally? I'd rather turn control of government over to a deep learning AI. Train it at the city level for awhile, then let it move up as it improves. At least the AI would make logical and rational choices.

We must dissent

How proud we have become... and how blind

[wierd]

Again, the government we deserve.

[Loud Whispers]

Nobody ever said this kind of government was ideal. Far the contrary I believe. Just that it is one of the better options available.
Personally? I'd rather turn control of government over to a deep learning AI. Train it at the city level for awhile, then let it move up as it improves. At least the AI would make logical and rational choices.

We must dissent

How proud we have become... and how blind

Science has gone too far
Fuck you Zhakarov, load the planet busters, space war now

[Akura]

What the hell did I start?



Anyway. I have no idea what I'm drinking. Bought a 7-Eleven Gulp(smaller than a Big Gulp) cup, pressed what may have been a button or something for lemon... something. Some carbonated yellowish drink came out. Looks kinda like ginger ale, but tastes vanilla-ey. Not that good though, might be diet.

[Rolan7]

Science has gone too far
Fuck you Zhakarov, load the planet busters, space war now

Nyet, nothing can stahp the progress!  Nothing- SWEET UNMERCIFUL SCIENCE, THE MINDWORMS

[Spehss _]

Personally? I'd rather turn control of government over to a deep learning AI. Train it at the city level for awhile, then let it move up as it improves. At least the AI would make logical and rational choices.

There's an Isaac Asimov short story similar to that. "The Evitable Conflict"

Rational is terrifying though. Depending on what it's meant to be optimising logical can go some very bad ways.

Indeed. It would be not so surprising if an AI identified humans as the weak, irrational and inefficient link in global society. Eliminating us could end crime, world hunger, war, and so on...

How logical.

And that's a standard sci-fi trope to justify the robot revolution against humans. "Humans are flawed, beep boop, better to remove humans than serve flawed meatbags, beep boop. Kill kill kill beeeeep."

[NJW2000]

I reckon that the machines will kill us all someday when the scientists build a network of robots and AIs to keep the whole wide world safe and happy, then some vote-greedy politician with no understanding of the system in question pledges to set such a low value for [MAXIMUM_HUMAN_SUFFERING_LEVEL_ACCEPTABLE] that our existence becomes unacceptably risky, and needs to end.

[Graknorke]

And that's a standard sci-fi trope to justify the robot revolution against humans. "Humans are flawed, beep boop, better to remove humans than serve flawed meatbags, beep boop. Kill kill kill beeeeep."

That... isn't what I meant. It's not so much that they'd want to get rid of humans as they wouldn't consider them the same way other humans do.
See: Stamp collecting AI thought experiment.

[wierd]

That's what I was getting at. AIs dont see "People", they respond to data.  Peoples lives are just more data to them. Depending on how the AI is programmed, and how information is fed to the AI, it could either be very beneficial for humans (who would finally have a truly impartial executor) or very detrimental (as that executor crushes all their dreams.)

That's why I suggested limited exposure as the first activation experience. Perhaps, management of a small group of human workers. Perhaps management of a project. Something that has quantifiable and predictable inputs to use as data, and which use human satisfaction as one of the optimization metrics.  (Note, NOT happiness, Satisfaction. Very different things)

So, the overriding goals of the Statesman AI 1.0 would be:

Keep crime within human tolerable levels, favoring lows
Prevent mismanagement of government resources
Optimize for human satisfaction, based on human input
Reduce contention between humans for resources
Prevent outcomes that would disfavorably impact human satisfaction.
Assure that all humans are treated equally in terms of legality
Respect human rights (including privacy and dignity)
Verify accuracy of all collected data