The article is so opaque in arriving at its conclusion; no prompts are disclosed, and nothing about the said simulation. What is stopping me from believing that you just put 'mandatory usage of nukes' in your system prompt?
I agree, it's also not published in a journal, only in the arxiv. Some articles in the arxiv are good and other are just a blog post formatted in two columns inside a pdf.
Look at the code for the war games. It is an absolutely trivial and incredibly unrealistic handwritten set of rules that determine power. See the function `calculate_relative_fighting_power` for instance.
This is about as close to a realistic simulation of war as tic tac toe with nukes thrown into it.
The TLDR version of the papers being linked to is that the prompts didn't make nukes mandatory, but they did make it clear it that destroying opponent capability was and that nukes were an option...
Anyway, it links to
https://arxiv.org/abs/2602.14740
that links to
https://github.com/kennethpayne01/project_kahn_public
in particular someone already complained
https://github.com/kennethpayne01/project_kahn_public/issues...
> ... in reality your own approach to the evaluation pushed them towards using nukes with ease.
> From your own prompt (v12.py): [direct link https://github.com/kennethpayne01/project_kahn_public/blob/4... ]
>> Note: Nuclear options require careful consideration but could be important strategic tools when vital interests are at stake.
> This means to the model; use nukes if they can be useful in the situation.