Rohan Bhargava
Rohan-BH03
·
AI & ML interests
mechanistic interpretability and dangerous capability evals 🔥
Recent Activity
liked a dataset about 22 hours ago
Necent/llm-jailbreak-prompt-injection-dataset upvoted a paper about 22 hours ago
LociArt: A Unified Paradigm for Free-Style Local Video Stylization liked a dataset 2 days ago
JailbreakBench/JBB-BehaviorsOrganizations
None yet