Our paper at EMNLP 2023, “Learning Interpretable Style Embeddings via Prompting LLMs” used GPT-3 to generate a synthetic dataset used for training interpretable text style embeddings, where each dimension of the embedding vector has a meaningful interpretation to a human.

Our paper at ICLR 2023, “Bidirectional Language Models Are Also Few-shot Learners” surprisingly discovers that older models like T5, that predate GPT-3, were promptable and could perform in-context learning.

Back in 2015, I discovered a surprising security vulnerability that allowed you to run malicious JavaScript code on the Google search engine results page, which might be one of the most secure pages on the internet given how much daily traffic it recieves.