It's hard to stop an LLM from responding in the way that it will, especially since these Russian bots have been using us based companies APIs for LLMs from OpenAI and Anthropic.

OpenAI and Anthropic can hardly stop their LLMs from giving bomb instructions, or participating in questionable sexual role playing that they would rather people not use their systems for. It's very hard to tame an LLM.

Of course Russians paying for these APIs can't stop the LLMs from acting how they normally would, besides giving them a side to argue on in the beginning.

You just don't understand the technology. (I don't either but I know more than you)