Do you actually know where your "identity" is stored in your local AI setup?
Is it in a markdown file? A system prompt? An Ollama config?
If you have three different files defining who you are, your LLM is working from a blurry, contradictory picture of you.
Stop guessing what’s running on your machine. I built an 8-step methodology to audit local AI layers.
Make the implicit explicit. https://wiobyrne.com/audit-your-local-ai-setup/