Yes
Yes. I participated in the Adversarial Nibbler Project, where I worked on evaluating AI-generated image outputs and identifying harmful or unsafe content. My responsibilities included creating prompts, reviewing generated images, selecting potentially harmful outputs, and classifying them according to categories such as attack mode, identity attributes, and content type. I also rewrote prompts when necessary and followed quality assurance and verification processes before final submission. This experience gave me hands-on exposure to AI data annotation, content moderation, AI output evaluation, and quality review workflows.
Not specified