SAFL AI Futures Dialogue #1 | Dr. Pulkit Verma
Title: Beyond the Lab: User-Aligned Assessment of Taskable AI Systems
Abstract: As AI systems increasingly serve non-expert users - from household robots to digital assistants that can alter their environments in risky ways - assessing their safety and reliability becomes critical. This talk explains why doing so requires more than extending existing verification methods and presents research directions and early solutions for formally evaluating such systems.
Speaker: Dr. Pulkit Verma is an Asst. Professor at the Dept. of CSE, IIT Madras, and the lead of the Human-Aligned Intelligent Learning Systems (HAILS) group. He works on the safe and reliable behavior of AI agents.
Date and Time: Aug 21 2026 (Friday), 5:30 PM onwards as part of the Technical AI Governance Reading Group at our Delhi hub.
Format: Virtual event, open to everyone.
To register for the reading group, please apply here.
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)