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

Atlas / People / Detail

Samuel Marks

Senior research engineer at Anthropic interested in agent foundations, model organisms of misalignment, and human-computer interaction.

Researcher1 organizations6 reports

Profile status: updated

updated 3 public sources

Public links

website Personal homepage github GitHub profile google_scholar Google Scholar profile

Organizations

core Anthropic

Reports

Alignment and Safety Many-shot Jailbreaking Alignment and Safety Alignment faking in large language models Alignment and Safety Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Interpretability On the Biology of a Large Language Model Interpretability Tracing the thoughts of a large language model

Official and primary sources

https://samuel-marks.com/ Official source · homepage https://scholar.google.com/citations?hl=en&user=Q-KQk40AAAAJ Official source · scholar

Supporting sources

https://github.com/samuelmarks Supporting source · github