AI chatbots tend to choose violence and nuclear strikes in wargamesylai@lemmy.ml to Not The Onion@lemmy.world – 216 points – 10 months agonewscientist.com54Post a CommentPreviewYou are viewing a single commentView all commentsSo 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! 🤯I learned it from watching you!Where are all these nuclear strikes?Sid Meier's Civilization gamesGhandi has the right idea.
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! 🤯I learned it from watching you!Where are all these nuclear strikes?Sid Meier's Civilization gamesGhandi has the right idea.
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! 🤯I learned it from watching you!
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! 🤯
I learned it from watching you!
Where are all these nuclear strikes?
Sid Meier's Civilization games
Ghandi has the right idea.