Now

Studying:

• Mechanistic Interpretability, and in general explainability for LLM and ML models.
• Statistics
• AI for biotechnologies
• Security

Building:

• Experiment on how differences in capability, status, and deceptive incentives shape cooperation among AI agents.
• Exploration of the differences and similarities between DiffusionGemma and its AutoRegressive twin.

Working:

• AI Engineer @ pillar.