Rui Komatsu
komatsurui
AI & ML interests
None yet
Recent Activity
upvoted a paper 27 days ago
WOLF: Werewolf-based Observations for LLM Deception and Falsehoods upvoted a paper about 2 months ago
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming
and Robust Refusal updated a model about 1 year ago
komatsurui/MyGemmaNPCOrganizations
None yet