We are looking for Humanities Expert candidates for a project delivered through Mercor.
What you'll do
- Writing a question from your own field, with the sources, the context, and the interpretive problem, plus the reference answer a model's attempt gets graded against
- Grading model-written interpretation and argument: whether the sources say what the model claims, whether the reasoning holds, whether the historical or cultural context is right
- Flagging where a model produces fluent, confident prose that misreads the text, flattens a live scholarly debate, or invents a citation
What you need
- Clear written communication, since most of the work involves explaining your reasoning
- Comfort with ambiguous tasks, and willingness to flag unclear instructions
Nice to have
- Humanities scholars with judgment and expertise to grade frontier AI
- Ability to tell a strong reading from a merely plausible one, and precisely state where the weaker one fails
Who you work with
Project and contracting process: Mercor. Applications continue on the provider's website.