I asked chatGPT to give me a solution to a real world prisoners dilemma situation. It got it wrong. It moralized it. Then I asked it to be Kissinger and Machiavelli (and 9 other IR Realists) and all 11 got it wrong. Moralized.

Grok got it right.

The current 5.2 model has it's "morality" dialed to 11. Probably a problem with imprecise security training.

For example the other day, I tried to have ChatGPT role play as the computer from War Games and it lectured me how it couldn't create a "nuclear doctrine".