Varun Iyer
Hi, I'm Varun, an independent AI safety researcher. I'm interested in AI inference, representation geometry, and developmental interpretability. Lately, I've been studying how misalignment-relevant structure takes shape during training.
I've co-founded three startups: Soma (AI inference marketplace), Glass (decentralized video, $1M+ to creators), and Spott (map-based social network). Earlier, neuroscience-inspired AI and a math REU on search engine algorithms at UChicago.
Recent writing
-
Linear Safety Probes Cannot Silence Features They Detect
You can build a safety monitor that perfectly spots dangerous behavior — then disable it, and the model does the dangerous thing anyway.
-
Fine-Tuning Silently Breaks AI Safety Monitors
Fine-tune a model and its safety monitor quietly stops working — even though every standard test still says it's fine.