Nicholas Schiefer

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

arXiv 2024

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

arXiv 2024

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

arXiv 2023

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

arXiv 2022

Discovering Language Model Behaviors with Model-Written Evaluations

arXiv 2022

Toy Models of Superposition

arXiv 2022

Constitutional AI: Harmlessness from AI Feedback

arXiv 2022

Jared Kaplan

co-founder / Chief Science Officer

Ethan Perez

Shauna Kravec

researcher

Sam McCandlish

founder

Samuel R. Bowman

Zac Hatfield-Dodds

researcher

Amanda Askell

researcher

Anna Chen

researcher

Catherine Olsson

researcher

Danny Hernandez

researcher