Sanjeevan Selvaganapathy

Computer Science & Software Engineering Honours graduate from the University of Western Australia. I work on AI safety — how humans and weaker agents maintain autonomy and calibration when interacting with more capable systems. Interests include gradual-disempowerment-flavoured evaluations of agentic systems, sycophancy and calibration failures in RLHF-tuned models, and capability-asymmetric multi-agent deliberation (scalable oversight in reverse).

Currently a research assistant at the Network and Social Influence Modelling (NASIM) lab at UWA, and contributing to an inherited UWA Medical School collaboration on paediatric penicillin allergy de-labelling. Unit coordinator and lecturer for CITX0001 Foundation Computing at UWA College.

Research, cv, Google Scholar, Email.