Professional Overview
I have two years of experience evaluating AI prompts and responses for helpfulness, truthfulness, and verbosity, as well as, evaluating sentiment and intent. I have taken part in several projects geared toward making AI models hallucinate on safety issues. Numerous projects have involved fact-checking responses on complex topics. I have also worked on annotation projects involving images and videos. Before this, I had 8 years of experience as a researcher for a Tech PR company. Additionally, I have worked as a content writer on numerous projects over the past 10 years.