100+ concrete projects and open problems in evals
Marius Hobbhahn — 2025-03-22 — Apollo Research — LessWrong
Summary
Announces a curated compilation of 100+ concrete project ideas and open problems in AI evaluations, collected from 20+ experts across major safety organizations to help researchers get started and coordinate in the field.
Source
- Link: https://lesswrong.com/posts/LhnqegFoykcjaXCYH/100-concrete-projects-and-open-problems-in-evals
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- capability-evals — Evals