Opportunity type
Internship
Cause areas
AI safety & policy
Routes to impact
Skill-building & building career capital
Learning about important cause areas
Testing your fit for a certain career path
Direct high impact on an important cause
Relevant aptitudes
Conceptual & empirical research
Location
Amsterdam, Netherlands
Description
- In this role, you'll conduct research evaluating AI models for dangerous capabilities and misalignment using existing evaluation frameworks.
- Reproduce existing model evaluations to establish your technical foundation.
- Apply evaluations to different models and publish findings in a short paper on arXiv and other platforms.
- Research and improve evaluation methodologies, potentially developing a "loss of control bench" with field experts.
- Work independently while collaborating with your supervisor and reaching out to experts and potential co-authors as needed.
Source: 80,000 Hours Job Board
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities