I’ve explored a lot in the domain of AI Safety, having built a test suite and toolkit named WalledEval with my mentor, Rishabh Bhardwaj.
I also had the privilege of attending the LM Safety Workshop 2025 in Singapore this year.
In addition, I had the privilege to attend the Opening Keynote of ICLR 2025 by Prof Zico Kolter from CMU. I have summarised my notes here: Building Safe and Robust AI Systems.