AI safety evaluations with Inspect
Update: 2025-06-16
Description
I'm back from holiday, and this week Tania and I talk about a project she completed as part of the ARENA AI safety curriculum to replicate the findings of evaluations on frontier AI capabilities.
Link to reasoning paper: https://arxiv.org/abs/2502.09696
Link to the Inspect dashboard: https://inspect-evals-dashboard.streamlit.app/
ARENA AI Safety course: https://www.arena.education/
Comments
In Channel
Download from Google Play
Download from App Store
United States00:00
00:00
x
