AI Safety Meet Up

Sessions

1. Navigating through AI Safety Ecosystem in India | By Aditya Raj, Founder of AI Safety India

What the field looks like from India. Which programs take applications from here. What technical work and governance work look like day to day. Where the open problems are.

2. Activation Steering in Language Models: From Representations to Behavior | By Anusha Mujumdar

Colab Link

Dr. Anusha Mujumdar is an AI safety researcher working on model behavior, interpretability, and safe decision making. She holds a PhD in Applied Mathematics and has co-authored 20 international peer reviewed papers and 21 patents. She previously founded and led the Trustworthy AI research program at Ericsson, before going on to lead AI research at Intuit.

3. Beyond the Black Box: Practical AI Auditing, Global Standards & Holding Frontier Models Accountable

Parishrut Jassal is the Founder & CEO of GovernAI, a TEDx speaker, and an empaneled Working Group Member on AI and Digital Governance for the Government of Himachal Pradesh. He is Certified in ISO/IEC 42001 by AIQI (United Kingdom Accreditation Service), In Algorithmic Auditing in Public Sector by the National Audit Office of Estonia, and AI & Technological Transformation by the UNESCO & Saïd Business School, University of Oxford.

He has trained over 3,500 public sector officials across 8 Indian states and apex institutions of Central Government including the Indian Institute of Public Administration (IIPA), CDAC and CPWD. He is a former Deputy Advisor, at International cooperation (Asia-Pacific) Educational Planning and Administration Domain of Ministry of Education, GoI.

He has served as an expert on the UNESCO RAM India Report, Facilitated the South Africa AI Safety Cohorts, and is a Team India Member of AI & Partners (UK) and ForHumanity (USA). His PhD is in the domain of AI Governance and SDG 16.

Also happening

Join AI Safety India WhatsApp Community

AI Safety India x Electric Sheep