Working on AI safety by creating AI agents who can cooperate with humans. Supervised by Professor Gillian Hadfield

Worked on machine unlearning from the perspective of prompting. Submitted publication to ICML 2024. Supervised by Professor Nicolas Papernot. ArXiv link: https://arxiv.org/abs/2402.00751

Working on defining the concept of memory for AI agents and creating new self-organizing memory structures. Paper release coming soon :). Supervised by Professor Animesh Garg

- First author of: Large Language Models Are Human-Level Prompt Engineers (https://arxiv.org/pdf/2211.01910.pdf)- Accepted to ICLR 2023 main conference- Oral presentation at NeurIPS 2022 FMDM- Winner of NeurIPS 2022 AI Risk Analysis Award ($50,000 prize pool)- Accepted to NeurIPS 2022 ML Safety- Supervised by Professor Jimmy Ba

Leading a team of 12 developers to create the world's most powerful personal finance planning software. Our goal is to give people a statistically significant confidence interval around the financial impact of purchasing their breakfast bagel 🥯

Led the AI research team of 5 at Triomics during a brief contract with WealthyPlanet Labs, developing an automated system for matching oncology patients with clinical trials

Research Intern under Professor Chul Min Yeum, developing computer vision software to autonomously assess neighbourhood flood risk

Advanced AI & Analytics Research Team