- 🔭 I research natural language processing and machine learning. I'm currently looking at:
- 🔒 LLM security: hazards manifest if we don't treat language models as unreliable and subvertible. Or as demons!
- 🛡️ Online harms: content safety, illegal information, CBRN risks and more. Enumerate risks with Language Model Risk Cards
-
🏢 I'm principal research scientist in LLM Security at NVIDIA for my day job where I lead garak, principal investigator of Strømberg NLP at ITU Copenhagen by night
-
🧑🎓 I’m still learning sizecoding
-
🎓 My research papers are on Google Scholar. Ask me about any of them!
-
🪶 I write NLP, machine learning, and language tech articles on my blog, Inter Human Agreement
