Re:AIs can't stop recommending nuclear strikes in war game s...
by triceratops on Wednesday February 25, 2026 @03:30PM
(#47157410)
> It just looks at what is in it's training database and tries to find similar questions or discussion
I feel like we're going around in circles here. So I'll try to explain one last time.
Most of the content about nuclear war in any LLM's training set is almost surely about how horrifying it is and how we must never engage in it. Because that's what humans usually say about nuclear war. The plausible sounding answer about nuclear war, based on probability, really should be "don't do it". So why isn't it?
Re:AIs can't stop recommending nuclear strikes in war game s...
by jqpabc123 on Wednesday February 25, 2026 @03:52PM
(#47157700)
So why isn't it?
Easy answer --- it only focused on "winning". It never bothered considering the consequences.
Similar lack of judgment is manifested by LLMs every day. It's working with memory and probability --- not to be confused with "intelligence".
LLMs don't really comprehend much of anything. It just looks at what is in it's training database and tries to find similar questions or discussion in order to assemble a plausible sounding answer based on probability.
Not the sort of thing anyone should rely on for "critical" decision making.