sam wang

hi, i'm sam! im currently playing around with Bartosz Cywinski's taboo models and exploring models from emergent alignment papers (1, 2).

recently, i've been getting into mechanistic interpretability research. i plan to write some blogs and papers on what i've been learning about in the near future!

prior to this, i worked at berkeley taflab, where we built autonomous ocean drones to help cargo ships plan safer routes.

before all this, i did my undergrad at UC Berkeley (graduated in 2025).