Pedro Sandoval
psando
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
upvoted
a
paper
about 2 months ago
DynaGuard: A Dynamic Guardrail Model With User-Defined Policies
liked
a Space
about 2 months ago
tomg-group-umd/DynaGuard
Organizations
None yet