What do you mean by “make” what do you want it to do that you aren’t getting.

Maybe some existing model via ollama - llama-uncensored?

Do you need to add context with some specific set of data, should it be retrieval based or tuned or cross trained?

Does it even need to be an llm? What are you trying to actually achieve?

From experience, that works even on soft furnishings

Binary data. In the case of lz it was a carefully “corrupted” archive.

To be fair, the title says more apps, not all apps…

Under the dock?

Its peg where I live 🤷

Turnwise and widdershins. I read it in a book once.