Atlas / Reports / Detail
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Alignment and Safety report from Anthropic with 7 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
2 reports
Liane Lovitt
Anthropic
Research scientist at Anthropic whose public work includes AI alignment, reinforcement learning from human feedback, and model behavior.
Researcher
6 reports
Samuel Marks
Anthropic
Senior research engineer at Anthropic interested in agent foundations, model organisms of misalignment, and human-computer interaction.
Researcher
8 reports
Ethan Perez
Anthropic
Research scientist at Anthropic focused on scalable oversight, AI safety, and language model evaluation; previously worked at New York University and Google.
Researcher
8 reports
Nicholas Schiefer
Anthropic
Member of Technical Staff at Anthropic and cofounder of Oulipo Labs, working on language model safety, evaluations, and scientific forecasting.
Researcher
3 reports
Alex Tamkin
Anthropic
Member of technical staff at Anthropic whose work focuses on language models, model understanding, and alignment.
Researcher
2 reports
Beth Barnes
Anthropic
President of METR and former team member at Anthropic whose work focuses on evaluating and forecasting frontier AI capabilities.
Researcher
1 reports
Alexey Nazarov
Anthropic
Member of technical staff at Anthropic focused on safe and reliable AI.