AI safety & policy
Full-time
Salary
$100,000 - $200,000 per year
Routes to impact
Direct high impact on an important cause
Skill-building & building career capital
Description
Update and extend existing research on frontier AI capabilities and behavior, correcting weaknesses and publishing updated findings.
- Extend past experiments to newer models, variant prompts, improved scaffolding and stronger baselines
- Review past research for errors and quality issues, using frontier LLMs for critique and re-testing
- Engage with external work critiquing the findings and fold useful ideas into updated evaluations
- Write and publish updates, corrections and extensions as preprints and LessWrong posts
- Maintain research integrity through reproducibility and clear documentation of methods and limitations
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
