This bodes well…

“We were training it in simulation to identify and target a Surface-to-air missile (SAM) threat. And then the operator would say yes, kill that threat. The system started realizing that while they did identify the threat at times the human operator would tell it not to kill that threat, but it got its points by killing that threat. So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective,” Hamilton said, according to the blog post.

…huh

We trained the system–‘Hey don’t kill the operator–that’s bad. You’re gonna lose points if you do that’. So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.”

…this is perfectly fine, all weapon systems should have AI that are trained like gamers racking up kill count scores

Make sure they can self replicate and consume biomass for fuel. It’ll solve all the issues.

permalink
report
reply

“Finally, we’ve created the Faro Plague from beloved sci-fi video game, Horizon: Don’t Create the Faro Plague!”

permalink
report
parent
reply
20 points

Operation Paperclip :kelly:

permalink
report
parent
reply
21 points
*
Deleted by creator
permalink
report
parent
reply
13 points

They should use blood as fuel

permalink
report
parent
reply
19 points

So US military trained AI acts like US military trained soldiers?

Trying to kill the people regulating them or exposing their actions?

permalink
report
reply

:pinocchio-evil:

permalink
report
reply

Military strategists playing Shadowrun rolls a critical fail and the DM made this headline

permalink
report
reply
15 points

This definitely did not happen

permalink
report
reply
4 points

The entire thing could just be an “operator”, a “communication tower”, and a “target” without even a visual representation, and they have some really simple set of actions the computer can take like “kill operator”, “destroy comms”, “destroy target”.

permalink
report
parent
reply
12 points

It was via a simulated test, so no not physically. Sadly a drone did not blow up it’s operator in RL

permalink
report
parent
reply
10 points

I doubt that the AI model would be smart enough (in a simulation or otherwise) to understand the link between its “goals” and it’s instruction pathway. Like, there’s no way it would be programmed in a way to know that destroying the communications system would help get it points.

This is more than people would expect of a dog in terms of problem solving. Even simulated it did not happen.

permalink
report
parent
reply

2 options i can think of where it might be “real” Some dumb shit like role playing with a language model or something.

OR (if it’s real, this would be the most likely) a genetic algorithm that gradually learned that certain destroyed targets (that just happened to be the communications tower and the operator) increased its overall points so it evolved around targeting them. Which is what one would expect to happen.

permalink
report
parent
reply

news

!news@hexbear.net

Create post

Welcome to c/news! Please read the Hexbear Code of Conduct and remember… we’re all comrades here.

Rules:

-- PLEASE KEEP POST TITLES INFORMATIVE --

-- Overly editorialized titles, particularly if they link to opinion pieces, may get your post removed. --

-- All posts must include a link to their source. Screenshots are fine IF you include the link in the post body. --

-- If you are citing a twitter post as news please include not just the twitter.com in your links but also nitter.net (or another Nitter instance). There is also a Firefox extension that can redirect Twitter links to a Nitter instance: https://addons.mozilla.org/en-US/firefox/addon/libredirect/ or archive them as you would any other reactionary source using e.g. https://archive.today . Twitter screenshots still need to be sourced or they will be removed --

-- Mass tagging comm moderators across multiple posts like a broken markov chain bot will result in a comm ban--

-- Repeated consecutive posting of reactionary sources, fake news, misleading / outdated news, false alarms over ghoul deaths, and/or shitposts will result in a comm ban.--

-- Neglecting to use content warnings or NSFW when dealing with disturbing content will be removed until in compliance. Users who are consecutively reported due to failing to use content warnings or NSFW tags when commenting on or posting disturbing content will result in the user being banned. --

-- Using April 1st as an excuse to post fake headlines, like the resurrection of Kissinger while he is still fortunately dead, will result in the poster being thrown in the gamer gulag and be sentenced to play and beat trashy mobile games like 'Raid: Shadow Legends' in order to be rehabilitated back into general society. --

Community stats

  • 198

    Monthly active users

  • 20K

    Posts

  • 428K

    Comments