Rohan Bhargava
Rohan-BH03
·
AI & ML interests
mechanistic interpretability and dangerous capability evals 🔥
Recent Activity
liked a model about 11 hours ago
mradermacher/Qwen3-1.7B-Jailbreak-reasoning-GGUF upvoted a paper about 11 hours ago
CoworkOS:Scaling Agent Coworkers for Real-world Automation liked a model 3 days ago
imwizard/redteaming_model_flanT5_classification_2Organizations
None yet