Report: USAF experimental drone simulation AI turned on human operator (1 Viewer)

[2009ring]

You realize that no one younger than Gen X gets that reference right?

Signed,
Matthew Broderick


LOL

 

[SystemShock]

It's because it's "utility function" prioritized maximizing "points" first and foremost and points are awarded only or at least primarily by hitting its targets. So, according to it's core programming, it's primary objective is to maximize points.

I got that, however, the program only knows what/who the operator is, where it/they are, and that it/they could be a target dependent on a count, because someone coded all of that into the program

It feels like whoever did this knew this would be the result and wanted to make a point. At least they definitely should have known after the first incident, but instead they just told it, it would lose points if it killed the human operator, so it got more creative by destroying the infrastructure around the human... a better way would have been to change the order of its priorities, or change it so that it gets points by receiving instructions by the human every x minutes and losing points if it does not - and have those points be worth more than the secondary objective of destroying targets.

But it didn't get "creative", the option to do so and how to do it if/when certain conditions were met (i.e., the scenario) was programmed into it.

Edit: just read Arathrael's post. LOL

​

 

[SystemShock]

For someone who supposedly works in tech, you have a very, very poor understanding of how all of this works.

Really? LOL.

Why don't you explain it to me?

 

[Buickman]

I'm going back to the Cute Puppies thread. I'm happy there.

 

[Doug B]

Well, that makes more sense, but is also very lame.

We're going to get a lot of "AI's gone rogue!!!1!1!JUAN!" stories over the next decade or so. Popular media can't interpret science -- and a purported AI mini-takeover is never going to be clear as a bell thing, laid out on a silver platter, requiring no nuance to understand.

 

[GW93]

If Star Trek has taught me anything, if an AI gets all full of itself, just ask it to solve a logical paradox and it will self-destruct.

 

[CoolBrees]

And if Independence Day taught me anything, it’s that we can make a virus (in my best Jeff Goldblum: a…..computer…virus) that can take down even alien technology so we good.