Yoshua Bengino spells out the dangers here very well, without hyperbole (Turing Award winner, etc.):
https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-che...
Now extrapolate that to LLMs RL-trained on many niche applications. Good and bad arguments available, but ultimately it seems like bot-vs-bot, as long as the bots are well trained for those niches.