Technology

59771 readers

3679 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 2 years ago

MODERATORS

AI chatbots tend to choose violence and nuclear strikes in wargames (www.newscientist.com)

submitted 10 months ago by L4s to c/technology

19 comments fedilink hide all child comments

AI chatbots tend to choose violence and nuclear strikes in wargames::undefined

you are viewing a single comment's thread
view the rest of the comments

[–] Arkaelus 21 points 10 months ago (3 children)

This says more about us than it does about the chatbots, considering the data on which they're trained...

[–] kromem 4 points 10 months ago* (last edited 10 months ago)

Yeah, it says that we write a lot of fiction about AI launching nukes and being unpredictable in wargames, such as the movie Wargames where an AI unpredictably plans to launch nukes.

Every single one of the LLMs they tested had gone through safety fine tuning which means they have alignment messaging to self-identify as a large language model and complete the request as such.

So if you have extensive stereotypes about AI launching nukes in the training data, get it to answer as an AI, and then ask it what it should do in a wargame, WTF did they think it was going to answer?

[–] bassomitron 3 points 10 months ago (1 children)

I'd say it does to an extent, dependant on the source material. If they were trained on actual military strategies and tactics as their source material with proper context, I'd wager the responses would likely be different.

[–] [email protected] 2 points 10 months ago* (last edited 10 months ago)

Totally. Properly trained AI would probably just flood a country with misinformation to trigger a civil war. After it installs a puppet government, it can leverage that countries resources against other enemies.

[–] Gradually_Adjusting 1 points 10 months ago (3 children)

Maybe... But, hear me out, what if it means you can win nuclear wars? 🤔

[–] [email protected] 2 points 10 months ago (1 children)

What if there are no winners in any wars?

[–] Gradually_Adjusting 2 points 10 months ago

Let's think here... I've always heard history is written by the victors, which logically implies historians are the most dangerous people on the planet and ought to be detained. 🧐

[–] [email protected] 2 points 10 months ago (1 children)

Lol .... to an AI, humans on any and all sides can't win a nuclear war .... but AI can.

[–] Gradually_Adjusting 1 points 10 months ago

I hope it's obvious I was being hugely tongue in cheek

[–] [email protected] 0 points 10 months ago* (last edited 10 months ago)

Not that I want one, but the propaganda around nuclear war has been pretty extensive.

Michael Chrichton wrote about it in the late 90s if I remember right. He made some very interesting points about science, the politicization of science, and "Scientism".

"Nuclear Winter" for example, is based on some very bad, and very incorrect, math.