Daniel Khashabi
danyaljj
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
Jailbreak Distillation: Renewable Safety Benchmarking
upvoted
a
paper
3 days ago
The Trickle-down Impact of Reward (In-)consistency on RLHF
upvoted
a
paper
3 days ago
Jailbreak Distillation: Renewable Safety Benchmarking