👋 Hi! I'm Nick Fram.

I'm an AI safety and alignment researcher.

I'm currently a Member of Technical Staff, Safety Lead at Reflection, where I lead a high-impact, mission-oriented safety research team working on:

• Safety Post-Training — model policy and refusal behavior
• Safety Research — including safety-related alignment, oversight, interpretability, and abliteration resistance
• Safeguards — adversarial robustness, plus open-source and internal deployment mitigations
• Safety Evaluations and External Testing — for a peek, see the Open Safety Framework, Beam Safety Technical Report, Iris Safety Evaluations, Systemic Risks (Biological Weapons, Chemical Weapons, Cyber Offense & Loss of Control), and many more

Previously, I was a Research Scientist at Google DeepMind and a Member of Technical Staff (Manager) at Anthropic, with work spanning CBRN and cyber safeguards, safety training, frontier capability evaluations, and alignment, among other things.