Home People Organizations Reports Fields Schools

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

Atlas / People / Detail

Sören Mindermann

Research scientist at Anthropic working on machine learning and AI safety.

Researcher1 organizations3 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 completeness47%

Public sources2

Official sources2

CountryUnknown

Last reviewedMar 13, 2026

Review outcomeUpdated

Official homepage Scholar profile

updated Unknown location 2 public sources

Latest review note

Added personal website, Google Scholar profile, and a short English bio from public profile information.

Public links

website Personal website google_scholar Google Scholar profile

Organizations

core Anthropic

Reports

Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Alignment and Safety Alignment faking in large language models Alignment and Safety Auditing language models for hidden objectives

Official and primary sources

https://www.sorenmindermann.com/ Official source · homepage https://scholar.google.com/citations?user=1s4hm0QAAAAJ&hl=en Official source · scholar

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