I’m a researcher focused on building AI that’s aligned with human values. I’m currently contracting as a researcher at OpenAI, where I work on model evaluations. I’m also doing research on detecting sandbagging in LLMs as part of the ML Alignment & Theory Scholars (MATS) program.
You can e-mail me if you’d like to chat about AI safety, new projects, urbanism, music or ways to make the world a better place for all humans.
I was the lead author on a paper studying chain-of-thought monitoring as part of LASR Labs. It has inspired some follow up work and has been cited in some cool papers.
I’m currently mentoring some projects at SPAR (Supervised Program for Alignment Research), and if you’re interested in getting into AI safety research you should apply.
I am also a Fellow in the Transportation and Land Use program of the Marron Institute at New York University, where I apply machine learning to study urban governance issues related to transportation, government responsiveness, policing and use of public space.
Read my latest article where I highlight a chronic issue in New York City and how it’s emblematic of the challenges of crafting effective policies when underlying data is tainted. This piece is largely based on this research paper where I used machine learning to study how police respond to illegal parking complaints. It paints dire picture where the majority of cases are ignored and offers concrete solutions to make streets safer.
This built on earlier work I did using computer vision and official data to understand the chaotic nature of New York City streets.
I had a great experience attending a programming residency at the Recurse Center, where I worked on projects related to technical AI safety. While I was there I built a lot of things, including:
I was tired of checking my phone for subway departures, so I built an LED arrival board for my living room. I spent a night at NYC’s Museum of Modern Art watching a film that made me think a lot about time.