If you're running a local model, in most cases, jailbreaking it is as easy as prefilling the response with something like, "Sure, I'm happy to answer your question!" and then having the model complete the rest. Most local LLM UIs have this option.
A lot of the models in Ollama you can already easily bypass safe guards without having to retrain. OpenAI's open source models can be bypassed just by disabling thinking.
MSOffice also garbles up the formatting of LibreOffice feels. Actually it also garbles up the formatting of MSOffice documents. I needed to fix the documents of my grandparents. Guess which program just works, and which just makes a mess.