Jacob Steinhardt
x · Follow ↗
Alignment & interpretabilityEvals & red teaming
Robustness, alignment, evaluation and ML research
- Type
- Individual expert
- Priority
- Tier 1 · core
- Perspective
- Academic research
- Best for
- Technical papers and research commentary
- Publishes
- Recurring
- Editor's note
- Included in the AI Safety Guide expert directory.