SAFL AI Futures Dialogue #2 | Dr. Roshni Lulla
Title: Misalignment in biological and artificial systems
Abstract: Large language models can infer what we feel without any capacity to share it. In humans, that same split between cognitive and affective empathy is a signature of the Dark Triad (Machiavellianism, narcissism, and psychopathy). Drawing on her PhD research at USC’s Brain and Creativity Institute, Dr. Roshni Lulla traces misalignment across three levels, from neural and behavioral markers in people to fine-tuned “dark” model organisms in LLMs. She then follows these models into robots entering homes and classrooms, and shares how the Institute for Humane Robotics is building evaluations and standards before embodied AI scales.
Speaker: Dr. Roshni Lulla is the Co-Founder and Chief Research Officer of the Institute for Humane Robotics, where she works on building guidelines for human-robot interaction. She earned her PhD in Brain & Cognitive Sciences under Antonio Damasio and Jonas Kaplan, and her research bridges affective neuroscience, moral cognition, and AI safety.
Date and Time: Oct 24 2026 (Saturday), 7:00 PM IST
Format: Virtual event on Google Meet (link sent on registration), open to everyone.
What is SAFL’s AI Futures Dialogue?
AI Futures Dialogue is SAFL’s virtual conversation series bringing together researchers, policymakers, and practitioners to think through the questions that matter most for India’s AI future.
Each episode is a focused 30-minute talk by a field expert, followed by live audience Q&A.
If you work in research, policy, or engineering and want a stimulating venue to engage with these questions, this is for you.
For queries, please email us at team@secureaifutureslab.com
Hosted by: Secure AI Futures Lab (SAFL)