Rohan Bhargava
Rohan-BH03
·
AI & ML interests
mechanistic interpretability and dangerous capability evals 🔥
Recent Activity
liked a dataset 1 day ago
CHATS-Lab/Persuasive-Jailbreaker-Data liked a dataset 1 day ago
Unbabel/Multilingual-Red-Teaming upvoted a paper 1 day ago
Narrow Multimodal Fine-Tuning Can Induce Emergent MisalignmentOrganizations
None yet