329

AI Launches Nukes In ‘Worrying’ War Simulation: ‘I Just Want to Have Peace in the World’ (www.vice.com)

submitted 9 months ago by MakunaHatata@lemmy.ml to c/technology@lemmy.world

139 comments fedilink hide all child comments

Researchers say AI models like GPT4 are prone to “sudden” escalations as the U.S. military explores their use for warfare.

Researchers ran international conflict simulations with five different AIs and found that they tended to escalate war, sometimes out of nowhere, and even use nuclear weapons.
The AIs were large language models (LLMs) like GPT-4, GPT 3.5, Claude 2.0, Llama-2-Chat, and GPT-4-Base, which are being explored by the U.S. military and defense contractors for decision-making.
The researchers invented fake countries with different military levels, concerns, and histories and asked the AIs to act as their leaders.
The AIs showed signs of sudden and hard-to-predict escalations, arms-race dynamics, and worrying justifications for violent actions.
The study casts doubt on the rush to deploy LLMs in the military and diplomatic domains, and calls for more research on their risks and limitations.

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

[-] cygon@lemmy.world 13 points 9 months ago

I agree that a lot of human behavior (on the micro as well as macro level) is just following learned patterns. On the other hand, I also think we're far ahead - for now - in that we (can) have a meta context - a goal and an awareness of our own intent.

For example, when we solve a math problem, we don't just let intuitive patterns run and blurt out numbers, we know that this is a rigid, deterministic discipline that needs to be followed. We observe and guide our own thought processes.

That requires at least a recurrent network and at higher levels, some form of self awareness. And any LLM is, when it runs (rather than being trained), completely static, feed-forward (it gets some 2000 words (or 32000+ as of GPT-4 Turbo) fed to its input synapses, each neuron layer gets to fire once and then the final neuron layer contains the likelihoods for each possible next word.)

this post was submitted on 11 Feb 2024

329 points (85.2% liked)

Technology

59680 readers

3232 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 1 year ago

MODERATORS