AI chatbots tend to choose violence and nuclear strikes in wargames

ylai@lemmy.ml to Not The Onion@lemmy.world – 216 points –
AI chatbots tend to choose violence and nuclear strikes in wargames
newscientist.com
54

You are viewing a single comment

So do humans.

Here's a wild thought. Maybe that's why the chat bot (I assume LLM) does it too, because it's been trained on us! 🤯