Subramanyam Sahoo
SahoobhAI
AI & ML interests
RL, AI Safety and AI Alignment
Recent Activity
published a Space 23 minutes ago
SahoobhAI/sycophancy-eval authored a paper 26 days ago
Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations authored a paper 26 days ago
Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF TrilemmaOrganizations
