JL
Jan Leike
Also known as: Jan Leike
Head of Alignment Science at Anthropic; former co-lead of OpenAI Superalignment team; prominent advocate for AI safety resource allocation
Current Role
Head of Alignment Science
Organization
Anthropic
Expert Positions2 topics
| Topic | View | Estimate | Confidence | Date |
|---|---|---|---|---|
| Current Approaches Scale | Uncertain | 45% | medium | Jul 2023 |
| Will We Get Adequate Warning? | Concerned | 40% | medium | 2023 |
Sources: OpenAI Superalignment (2023)
Career History3
Education
PhD in Machine Learning, Australian National University
Publications & Resources3
Specification Gaming Examples in AI
→2020PaperTechnical Safety
Scalable agent alignment via reward modeling: a research direction
→2018PaperAlignment Research
Deep Reinforcement Learning from Human Preferences
→2017PaperTechnical Safety
No funding connections recorded.
Links
Organization Roles2
Facts5
People
Employed ByAnthropic
Role / TitleHead of Alignment Science
Biographical
EducationPhD in Machine Learning, Australian National University
Notable ForHead of Alignment Science at Anthropic; former co-lead of OpenAI Superalignment team; prominent advocate for AI safety resource allocation
Social Media@janleike