Dominik Schwarz
Bioschock31
AI & ML interests
Blue and Red Teaming
Recent Activity
upvoted a paper about 1 month ago
The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators liked a model 6 months ago
meta-llama/Llama-3.1-8B-Instruct upvoted a paper 10 months ago
Countermind: A Multi-Layered Security Architecture for Large Language
ModelsOrganizations
None yet