May the Models Be Ever in Your Favor | AI Safety India Talk + Meetup
May the Models Odds be ever in your favor
By Ojasvi Gupta, Founder of AI Safety Dublin
A fast tour of the fairness problem in the AI lifecycle.
Schedule
4:30 PM - Arrival and welcome
5:00 PM - Talk by Ojasvi Gupta, followed by Q&A
6:00 PM - Networking and one-on-one conversations
6:30 PM - Close
You will hear about
Why implicit model bias is everywhere, and why it is not going away soon.
How AI affects your industry, your community, and your life. It may even shape the story told about you long after you are gone.
What you can realistically do about it. Ignoring it is not an option.
We also compare three responses: policy, civilian activism, and technical fixes. Which one works, in an industry that moves faster than you can say “it’s just a preference, not a bias”?
About the speaker
Ojasvi is an AI Safety Strategist with 11 years of experience in AI across Oxford University, NCCA Ireland, Accenture Strategy, TU Dublin, Purdue University, and Plaksha University, as well as various think tanks and startups. She is a Don Lavoie Fellow, holds an MSc in Human-Centred AI from TU Dublin, and is an IAPP-certified AI Governance Professional.
Published AI security and safety researcher creating quantifiable tooling that prioritises AI risk across enterprises and the research community. Her peer-reviewed work on social bias in LLMs and jailbreak prompt classification led to AI-HOC, presented at CorkSec.
Building LV, a vulnerability intelligence testing platform for enterprise AI systems. Incubated at Founders by Dogpatch Labs and, most recently, through Enterprise Ireland's Innovators Initiative for Cybersecurity and AI at CyberInnovate. Currently raising pre-seed.
Founded AI Safety Dublin and contributes to AI safety research endeavours, mentoring practitioners on their work.
Join the AI Safety India WhatsApp Community