LLMpeople

Home People Organizations Reports Fields Schools

Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Jan Leike

Anthropic researcher focused on AI safety, alignment, and auditing hidden objectives in language models.

Researcher1 organizations2 reports

Profile status: updated

Suggest a correction

Suggest a source

Contributions are treated as untrusted leads. Public changes happen only after review against public sources.

Trust signals

Profile completeness45%

Public sources2

Official sources1

CountryUnknown

Last reviewedMar 13, 2026

Review outcomeUpdated

Official homepage

updated Unknown location 2 public sources

Latest review note

Added Anthropic profile and interview links plus a source-grounded AI safety and alignment bio tied to hidden-objectives auditing.

Public links

website Official team profile news Anthropic interview

Organizations

core Anthropic

Reports

Alignment and Safety Auditing language models for hidden objectives Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Official and primary sources

https://www.anthropic.com/team/jan-leike Official source · homepage

Supporting sources

https://www.anthropic.com/news/jan-leike-on-what-human-level-ai-means-for-safety-and-alignment-research Supporting source · news

LLMpeople is a public atlas for discovering frontier AI researchers with context, provenance, and respect.