Beth Barnes
x · Follow ↗
Evals & red teamingAlignment & interpretability
Scalable oversight, model evaluations and safety research
- Type
- Individual expert
- Priority
- Tier 1 · core
- Perspective
- Evaluations / alignment
- Best for
- Research and evaluation updates
- Publishes
- Recurring
- Editor's note
- Included in the AI Safety Guide expert directory.