News for hackers. Stuff that matters.

A comment on AIs can't stop recommending nuclear strikes in war game simulations. Parent comment

Re:AIs can't stop recommending nuclear strikes in war game s... by Sharlin on Wednesday February 25, 2026 @09:29AM (#47151956)
It's "surprising" because there's supposed to be this thing called "alignment" which in general is supposed to make AIs not do such things.

If the headline were the less interesting "AIs never recommend nuclear strikes in war games", people on HN would probably ask "how is that surprising, that's what alignment is supposed to be?"

In any case, we're extremely lucky that there's about 0.001% probability of LLMs being a path to AGI.

[ Parent | on HN ]
Re:AIs can't stop recommending nuclear strikes in war game s... by jqpabc123 on Wednesday February 25, 2026 @09:47AM (#47152236)
In any case, we're extremely lucky that there's about 0.001% probability of LLMs being a path to AGI.

It's pretty safe to say that AGI requires a lot more than picking plausible words using probability.

The danger is the number of people in positions of leadership who don't get this. People who are easily seduced by the "fake intelligence" of LLMs.

[ Parent | on HN ]