ValnaoAIs can’t stop recommending nuclear strikes in war game simulations
The atrocities at Hiroshima and Nagasaki have been hand-waved extensively in writing — the same writing that AI is trained on. So naturally, AI will recommend the atrocity that has been justified by “instantly winning the war” and “saving millions of lives.”
These are word-probability glorified autocorrectors being prompted to “simulate” a nuclear war scenario. What words are going to show up a lot when discussing nuclear war? Launching nukes. Because that’s what all the literature about it has happen.
Once again, decision making and reasoning is being attributed to something that operates off of word frequency