✳flâneur — a map of the web's best reading
Hello - Cath Ge-Wang - Cath Ge-Wang
cjgwang.github.io · 397 words · saved by 1 readers
Cath’s research website
Hi! I’m Cath Ge-Wang, a mathematics undergraduate at Christ Church, University of Oxford. I’m currently working on building misalignment continuation evals with my mentors at UK AISI, will be working on verification protocols at MIRI, and previously was a part-time research collaborator at Redwood Research. I run the Oxford AI Safety Initiative’s Policy Team. My primary research interests lie in AI control and agent foundations, particularly understanding and mitigating emergent misalignment risks in autonomous AI systems. I focus on empirical questions around goal misgeneralisation, alignment
Explore this link on the map →related reading
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Teaching Claude why \ Anthropicanthropic.com
- Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Spring 2026 Projects - SPARsparai.org
- The Case Against AI Control Research — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Off Target | CNAScnas.org
- Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
- Recent Redwood Research project proposals — AI Alignment Forumalignmentforum.org