Public Blog/Website
Hi, I’m Avery. I’m a longtime product engineer turned AI researcher. I’m a Research Assistant to David Bau, a member of MIT AI Alignment (MAIA), and pursuing my MS in Computer Science at Northeastern University, studying human-AI interaction and AI safety.
Before transitioning to AI research, I spent over 12 years as a software engineer, with my longest tenure at Pivotal Labs.
I believe understanding how AI systems behave with and against human interests is the most fundamental and urgent AI research question.
I develop tools and studies that help humans understand, audit, and shape AI systems to benefit all humans.
Multi-Agent Social Deception Arena (project lead): Evaluation platform for testing strategic deception and persuasion capabilities in frontier LLMs using a well-loved social deduction game. Live leaderboard continuously benchmarks ChatGPT, Claude, Gemini, DeepSeek, Kimi, and other models. Forthcoming study of long-horizon multi-turn social gaming.
Agents of Chaos OpenClaw/Agentic AI red-teaming study where we expose a lot of urgent problems with agentic AI and suggest research directions.
National Deep Inference Fabric: The NSF National Deep Inference Fabric (NDIF) is a research computing project that enables researchers and students to perform mechanistic interpretability research on models, with sizes up to a 405B parameter open-weight model.
I’ve been playing classical cello since I was about 7, having previously subbed with the Boston Philharmonic, and continue to play today as part of the Mercury Orchestra and various other groups.
Feel free to find me on LinkedIn.