Aaron Tucker
Technical Lead
Aaron Tucker is the Technical Lead at FAR.AI, supporting the team to deliver research results.
Aaron completed a PhD at Cornell University advised by Thorsten Joachims, where he researched data-efficient preference feedback for search, recommendation, and LLMs, as well as eclectic interests in AI Governance and the intersection of common law and LLMs.
Previously, Aaron built Sendwave’s antifraud system, interned at UC Berkeley’s CHAI and Microsoft Research, and was a 2019 GovAI Summer Fellow.
NEWs & publications
Layered AI Defenses Have Holes: Vulnerabilities and Key Recommendations
July 2, 2025
defense-in-depth
STACK: Adversarial Attacks on LLM Safeguard Pipelines
stack-adversarial-attacks-on-llm-safeguard-pipelines
Pacing Outside the Box: RNNs Learn to Plan in Sokoban
July 24, 2024
pacing-outside-the-box-rnns-learn-to-plan-in-sokoban
Planning behavior in a recurrent neural network that plays Sokoban
planning-behavior-in-a-recurrent-neural-network-that-plays-sokoban
STACK: Adversarial Attacks on LLM Safeguard Pipelines
July 2, 2025
stack-adversarial-attacks-on-llm-safeguard-pipelines
Layered AI Defenses Have Holes: Vulnerabilities and Key Recommendations
defense-in-depth
