arxiv:2504.07092
Alexander Rubinstein
arubique
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
upvoted
a
paper
about 2 months ago
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
commented on
a paper
about 2 months ago
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
Organizations
None yet