Prompt and Response Writing and Evaluation
I worked on many different projects training LLMs. I have worked with GPT-3, GPT-4, Falcon, Llama, Gemini, LaMDA as well as other. My jobs consisted of generating and evaluating prompts and responses for factual accuracy, harmlessness and adherence to constraints. I have some brief experience with red teaming, but would love to expand my skills in this area.