About James Chua
- published
Me
Hi! Currently I’m working as an alignment researcher at Owain Evans’ org. Previously I’ve worked as a machine learning engineer (LeadiQ 2020-2023), and as a MATS 2023 scholar under Ethan Perez. I enjoy making typesafe python packages such as Slist on the side.
My research
- Looking Inward: Language Models Can Learn About Themselves by Introspection
- Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
In progress
- Language Models Can Articulate Their Implicit Goals
Links:
Google Scholar | Github | chuajamessh < dot > gmail.