菅原 祐介
sugayusuke
·
AI & ML interests
safety evals
Recent Activity
upvoted a paper about 3 hours ago
Measuring AI Agents as Teammates with Collaborative Intelligence liked a dataset 1 day ago
andersonbcdefg/red_teaming_reward_modeling_pairwise liked a dataset 1 day ago
CHATS-Lab/Persuasive-Jailbreaker-DataOrganizations
None yet