Sleeping
Agents
Build Your Own SafeTulu
🛡
Filter safety-harming data out of Tulu 3 at any threshold
Saket Reddy
SaketR1
AI & ML interests
None yet
Recent Activity
authored a paper about 20 hours ago
Follow the Gradient: Tracing Safety Degradation Back to Training Data authored a paper about 20 hours ago
BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization upvoted a paper about 21 hours ago
Follow the Gradient: Tracing Safety Degradation Back to Training DataOrganizations
