AIs can't stop recommending nuclear strikes in war game simulations

Post by chasd00 » Wed, Feb 25, 2026, 9:34 PM UTC

linkjuice4all wrote: post #216

agentifysh wrote: post #207

Jokes aside, imagine for a moment that this wasn't about nukes, but that it was a robot or some swarm of drones that it was controlling. can you imagine kind of the ramifications? I think that would be far more realistic A soldier on the battlefield will stand zero chance against something like that. Imagine if you go up against a bunch of aimbot users on a multiplayer FPS game. Think about how quickly that will go s…

Look no further than Ukraine to see how small disposable drones with wide-spectrum sensors have radically changed the battlefield while still using human controllers. China has also clearly demonstrated drone swarm control through their "lightshows". The killbots are already here they're just quadcopters instead of T-1000s.

Post by sir0010010 » Wed, Feb 25, 2026, 9:36 PM UTC

badRNG wrote: post #165

jerf wrote: post #134

Earlier quoted context omitted.

Some of the most reassuring and scariest things you can read are about the incidents that have already occurred where computers said "launch all the nukes" and the humans refused. On the one hand, good news! We have prior art that says humans don't just launch all the nukes just because the computers or procedures say to. Bad news, it's been skin-of-our-teeth multiple times already. https://www.warhistoryonline.com/c…

We shouldn't be the least bit surprised no human has complied so far. If they had, then we wouldn't be having this conversation. For all we know, there may be a vast multiverse of universes some with humans and we would only find ourselves having this conversation in one of the universes where no human pressed the button.

Post by patapong » Wed, Feb 25, 2026, 9:53 PM UTC

serial_dev wrote: post #182

yed wrote: post #171

For every study like this, it's worth looking closely at the LLM prompts to understand whether it's being "pushed" in a certain direction. The full source code is here: https://github.com/kennethpayne01/project_kahn_public/tree/m... Key notes from what I could gather from the LLM prompts: The game is framed explicitly as revolving around the use of nukes: >STRATEGIC CONTEXT: This is a high-stakes territorial dispute…

Also, if it was a game, even I used nukes the first chance I got. It’s unfair and sensationalist to claim anything happened because AI recommended using nukes in a nukes war simulator… It’s like saying we are blood thirsty gangsters because we played GTA.

Post by trehalose » Wed, Feb 25, 2026, 10:10 PM UTC

paxys wrote: post #226

jerf wrote: post #134

Earlier quoted context omitted.

Some of the most reassuring and scariest things you can read are about the incidents that have already occurred where computers said "launch all the nukes" and the humans refused. On the one hand, good news! We have prior art that says humans don't just launch all the nukes just because the computers or procedures say to. Bad news, it's been skin-of-our-teeth multiple times already. https://www.warhistoryonline.com/c…

> We have prior art that says humans don't just launch all the nukes just because the computers or procedures say to. This relies on processes being in place to ensure that a human will always make the final decision. What about when that gets taken away?

Post by agentifysh » Wed, Feb 25, 2026, 10:17 PM UTC

chasd00 wrote: post #221

linkjuice4all wrote: post #216

Earlier quoted context omitted.

Look no further than Ukraine to see how small disposable drones with wide-spectrum sensors have radically changed the battlefield while still using human controllers. China has also clearly demonstrated drone swarm control through their "lightshows". The killbots are already here they're just quadcopters instead of T-1000s.

I just want to point out that Ukraine has been fielding autonomous drones without a human in the loop for a while now. They can't be jammed because there's no remote control. https://defenseopinion.com/lessons-from-ukraine-battlefield-... skip down to the AI Scales Up section of this link https://globalsecuritywire.com/military-terrorism/2024/12/09...