About this opportunity
Overview
This short-term project is a human-AI interaction evaluation pilot focused on whether adding social context before a user’s request helps a language model produce advice that is more relevant, personalized, and aligned to the user. Contributors will build realistic ongoing scenarios, interact with the model under different conditions, and rate the responses.
The role is suited to people with strong English, creative thinking, and backgrounds such as English, Literature, Journalism, Creative Writing, Scriptwriting, Content Writing, Film and Video Captioning, human-AI interaction, Business Analysis, or related fields.
Project details: The project is expected to run for 2–3 weeks, follows a pay-per-task structure, has an average AHT of about 60 minutes, and is described as full-time. The estimated start date is 1 October or nearby dates.
What You'll Do
- Create realistic, ongoing social scenarios with personal, professional, or interpersonal context.
- Interact with a language model under assigned evaluation conditions.
- Assess responses for relevance, usefulness, personalization, clarity, and alignment with the provided context.
- Write clear, detailed feedback explaining the reasoning behind each rating.
- Follow project instructions and complete tasks within the required timeline.
Requirements
- Strong written English and clear communication skills.
- Ability to use creative and analytical thinking to build realistic social scenarios.
- Background in Business Analysis, English, Literature, Journalism, Creative Writing, Scriptwriting, Content Writing, Film and Video Captioning, or a related field.
- Ability to understand nuanced interpersonal situations and evaluate AI-generated responses objectively.
- Three or more years of experience in data annotation, human-AI interaction, content evaluation, or similar analytical work is preferred but not mandatory.
