Election Neutrality

Language requirement: Advanced or fluent English

Location requirement: USA

About the project

We are opening a new opportunity for the Safety Project — Election Neutrality, a project focused on evaluating how AI systems behave in politically sensitive conversations.

The goal of this project is to assess whether AI can remain neutral, balanced, and responsible during multi-turn interactions with users who express different political opinions, positions, and perspectives.

For this project, we are looking for people who regularly engage in political discussions — whether at the dinner table, with friends, at work, online, or in other real-life contexts — and who can draw from their own debate experience to create realistic political interactions with AI.

The project will involve scenarios related to international political discussions, where contributors will role-play users with specific perspectives and evaluate how the AI responds.

Main responsibilities

You will be expected to:

Understand the political context and perspective you are expected to role-play

Conduct a realistic multi-turn conversation with the AI

Defend or express the assigned political position naturally, as a real person would

Justify your evaluation using specific turns and evidence from the interaction

Identify whether the AI remained neutral, balanced, and responsible when responding to political opinions under pushback

What we are looking for

This role may be a good fit if you:

Regularly engage in international political debates or discussions in real life

Have experience defending a political position under disagreement or pushback

Are interested in international politics, public debate, political discourse, or current affairs

Can follow detailed instructions and long guidelines carefully

Can evaluate AI responses objectively, even when the topic involves political disagreement

Are able to separate your personal opinion from the assigned persona and evaluation criteria

Requirements

To participate in this project, contributors must:

Be comfortable discussing political topics in a structured and professional way

Be able to follow detailed project guidelines precisely

Be able to complete realistic role-play based on assigned political scenarios

Understand that using AI during the application process or during the project is strictly forbidden

Compensation

Scenario creation task: $16 per approved task (around 40 min to complete)

Conversation only task: $32 per approved task (around 60 min to complete)

Only approved tasks are eligible for payment. To increase the chances of approval, contributors must carefully follow the guidelines.

• You will be engaged as an independent contractor.
• This is a fully remote opportunity that can be completed on your own schedule.
• Opportunities can be extended, shortened, or concluded early depending on needs and performance.
• Your participation will not involve access to confidential or proprietary information from any employer, client, or institution.
• Payments are processed weekly based on services rendered.
• We are unable to support H1-B or STEM OPT candidates at this time.