Hi, I'm LuisMi 👋

Aspiring AI Safety researcher, bridging alignment and interpretability

I deeply believe that through understanding the inner workings of AI systems, we can make them more aligned with human values.

luismmonh@gmail.com

Find me elsewhere

Featured Projects

Current work and key tools

Project log for my MATS 9.0 application work probing how latent content and behavioral inhibition interact inside Taboo-fine-tuned Gemma models.

Tech Stack