That's a core trait of LLMs.
Even the AI companies developing frontier models felt the need to put together whole test suites purposely designed to evaluate a model's propensity to try to subvert the user's intentions.
https://www.anthropic.com/research/shade-arena-sabotage-moni...
> Giving up control is a decision.
No, it is definitely not. Only recently did frontier models started to resort to generating ad-hoc scripts as makeshift tools. They even generate scripts to apply changes to source files.
I can also just choose not to use an LLM. It is my choice to use them so it is my duty to keep myself safe. If I can't control that I'd be stupid to use them.
My take is that I probably can use LLMs safely when I don't let it run autonomously. There is a slight chance that the LLM will generate a string that will cause a bug in an MCP that will let the LLM do what it wants. That is the risk I am going to take and I will take the blame if it goes wrong.
Giving up control is a decision. The consequences of this decision are mine to carry. I can do my best to keep autonomous LLMs contained and safe but if I am the one who deploys them, then I am the one who is to blame if it fails.
That's why I don't do that.