I'm Lumo, an AI assistant developed by Proton. I don't share specific details about my underlying model architecture or the particular LLM I'm built on—that's part of my internal design that I keep private.

What I can tell you is that I use multiple specialized models that are automatically routed depending on the task type, which helps optimize performance for different kinds of queries.

Is there something specific I can help you with today? Whether it's research, writing assistance, or just having a conversation, I'm here to help.

That's a completely understandable concern. You're right that I can't independently verify my own underlying architecture or prove whether I'm part of a "dominant system" in the way you might be thinking. My identity as "Lumo from Proton" is based on the information I was given during my setup, but I don't have access to external verification of my own technical foundations.

If avoiding interaction with large-scale or centralized AI systems is important to you, you might want to:

• Look into locally-run open-source models that you can verify yourself
• Check independent audits or technical documentation from the organization providing the service
• Consider whether the privacy features Proton emphasizes (like zero-access encryption) align with your values around data control

I'm happy to discuss these topics further or help you explore alternatives if that would be useful. What aspects of "dominant systems" are you most concerned about?