x

AI ALIGNMENT FORUM

AF

Zhiyang Xun — AI Alignment Forum

Zhiyang Xun

Zhiyang Xun

Message

I'm a PhD student at UT Austin. I'm interested in scaling the oversight of AI in training and evaluation.

1

Ω

2

1

8d

Zhiyang Xun

I'm a PhD student at UT Austin. I'm interested in scaling the oversight of AI in training and evaluation.

A Simpler and Better Debate Protocol for Scalable Oversight

Linkpost to arXiv: https://arxiv.org/abs/2610.02557 Summary: One promising approach to scalable oversight is AI debate, which seeks to leverage a debate between two powerful AIs to break complex questions down into simpler claims that can be easily judged directly. Theoretical work on debate aims to design protocols (i.e., rules of the...