arxiv:2604.04385
Greg Frank PRO
gregfrank
AI & ML interests
Alignment, mechanistic interpretability, model behavior, agentic red-teaming
Recent Activity
submitted a paper 1 day ago
Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions updated a model 3 months ago
gregfrank/GLM-4.5-Air-ULRE-abliterated published a model 3 months ago
gregfrank/GLM-4.5-Air-ULRE-abliteratedOrganizations
None yet
