Nick Meyer
I'm a Masters student in Computer Science at Columbia University. I’m focused on AI safety and alignment, where I hope to help ensure the technology is developed safely and ethically. Recently, I've been concentrating on questions related to value alignment, (dis)empowerment, safety evaluations, and scalable oversight. I also have deep interests in moral, political, and existentialist philosophy and am keen to help strengthen the connection between philosophy and technical AI safety.
I spend a lot of time thinking, but at the end of the day, to me, life is all about feeling. Like many people in this field, I’m drawn to working on things that both excite me intellectually and bring about a feeling of muditā*.
I'm thankful for the people, art, and experiences that make me feel something real. The warmth of vulnerability with a close friend. The rapture of a rolling bassline reverberating through my chest. That first sip of black coffee† on a slow morning.
Poke around and get to know me :)
Introspection Fine-Tuning
Replicated IFT, developed an improved objective function, and fitted jacobian lenses on Llama 3.2 and Qwen3.
Harmlessness Finetuning
Finetuning Llama 3.2 1B with SFT and DPO + LoRA for improved harmlessness.
Cambridge Alignment Bootcamp
My work through the ARENA curriculum in interpretability and alignment as part of CBAI's CAMBRIA program.
Corporate Orthogonality
Structural misalignment and the limit of technical approaches.
Dimensionality Reduction
A comparison of PCA and linear autoencoders on MNIST.
What are we building for?
Artificial intelligence, alignment, and building a future worth wanting.
Input-Attribution Methods Cannot Justify AI Decisions
Mechanistic interpretability as the path forward towards achieving a duty of justification.
We Have Yet to Cut Off the Head of the King
A misdiagnosis of power and Foucault's challenge to domination theory.
