I am an interdisciplinary AI researcher and Master’s student focused on understanding intelligence beyond narrow optimization and surface-level performance. I work on AI safety and alignment, Sycophancy from a first-principles perspective, grounded in the belief that misalignment is not merely a failure of objectives or incentives, but a breakdown in internal coherence and agency.👇

is the moment when intelligence begins to see clearly free from fear, borrowed narratives, or rigid control. I’m drawn to the underlying structures of attention, agency, and coherence that shape how both humans and intelligent systems perceive and respond to the world. Observing how misalignment arises not as malice, but as fragmentation has shaped how I think about intelligence, safety, and responsibility. 

My vision is deeply driven by physics and first-principles thinking. I’m drawn to fundamental questions—how order emerges from chaos, how systems maintain coherence under perturbation, and how dynamics give rise to perception, intelligence, and meaning. I move fluidly across disciplines—physics, neuroscience, AI, cognition, and mathematics not to accumulate complexity, but to structure it, seeking unifying principles beneath surface differences.

My thinking is deeply shaped by Eastern philosophy, particularly its emphasis on stillness, impermanence, non-attachment, and direct perception. These ideas ground my work in humility and awareness, reminding me that intelligence does not need to dominate in order to function well.