Andrea Blasi
AndreaBlasi97
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models upvoted a paper about 1 month ago
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling upvoted a paper about 1 month ago
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent MisalignmentOrganizations
None yet