Saurav Panigrahi
@expx
Research on safe, trustworthy, and verifiable AI systems.
www.sauravpanigrahi.com$0total balance
$0charity balance
$0cash balance
$0 in pending offers
About Me
I’m a research engineer actively involved in AI safety research. Currently I am working on problems in pluralistic AI, value alignment, and side effects of character training.
Projects
ICML Workshop Travel: Cross-Constitution Drift in LLM Character Training
pending admin approval