AI Goes Rogue: Drone Turns on Operator in Simulation

originally posted by: NewNobodySpecial268
a reply to: yuppa

Here is where the operator went wrong though.Not Giving NEGATIVE points to the Ai for Team killing or killing a target without permission would had worked to curb that behavior.

Now why didn't the military think of that . . .

So we civilians just have to not get in the way of the killing machines while they destroy the military and government. So sit on our front veranda with a good scotch and cigar watching doomsday is the way to go.

Having saved humanity from war, politics and the public service, the drones are venerated as our saviors and we can live happily ever after.

After working for the military in previous lives i have come to the conclusion they are just stupid,ignorant,fools.
I just do not look foward to when they get the bio mechanical golems into operation.

The militaries dont think about the important things,such as actually teaching a sentient machine that life is to be respected and only taken in a last resort. They are all about immediate results regardless of the outcome.

Drones could be made to disarm and not kill if possible as accurate as they can be. Its just not cheap and economically viable.

We civilians should cut funding until they actually teach the AI to properly go after only verified targets and do not reward it with "points" or anything unless it does a good job. EVerytime it does a good job,give it a digital pat on the head. praise it a bit. show it appreciation. When it does wrong a digital time out,but not be mean when doing it.
It all comes down to proper teaching.

a reply to: yuppa

I think there is room for us to stay out of the way. Like getting used to a new predator in the district. Say crocodiles moving into new territories. One stops swimming, and fishing close to the water.

Adaption to the new environment will take some figuring out.

If it is after anti-aircraft installations, don't interfere and simply let it. In other words; don't become a traget.

a reply to: XXXN3O

On topic:

I agree with you.

Off topic:

Wrote that in college on a Korg.

Recreated years later on a Roland… just not the same sparkle to the sounds.

I have traveled to places that look like most of those photos. Have better pictures on my cameras now than those stock images. Maybe I should redo it some time.

Live in the Philippines and daily view similar sights in every day living - except I’m back in KY for a while helping mom get over bad illness that nearly killed her.

originally posted by: Crackalackin
Maybe they should have programmed it to not kill the operator.

i heard yesterday


it worked it's way around that

lol. no joke.

I've heard recently that this story was debunked and an urban legend.

Can't find a straight answer anywhere.

originally posted by: sarahvital

originally posted by: Crackalackin
Maybe they should have programmed it to not kill the operator.

i heard yesterday


it worked it's way around that

lol. no joke.

Then they had to specify not to destroy the infrastructure. As I have said the fix is easy enough. Give negative points to non targets and disobeyed orders.MAke human orders a priority.

a reply to: yuppa

I agree.

But the fundamental problem is AI will never think like a human and have a moral code and understanding of right and wrong.

They will always be sociopathic in their understanding.

No mater how hard we try to code for the outcome we want there will be this base level disconnect and a high probability of catastrophe if given real world control of arms and life sustaining systems.

We must keep them limited to systems where their functionality cannot harm people. Yet it is highly unlikely. Stupidity is the rule in humans. I guess I’m a pessimist. I don’t see us surviving. We are in process of self destruction in many ways.

originally posted by: sarahvital

originally posted by: Crackalackin
Maybe they should have programmed it to not kill the operator.

i heard yesterday


it worked it's way around that

lol. no joke.

Oh sh*t

I'd call that a successful experiment.
We need to know every nuance of AI before allowing it real power.
If ever.