Yixiong Hao

I'm trying to write more as a way of improving my thinking. I cross-post on Substack and LessWrong. Also, check out my Curius profile!

2026

• We need a better way to evaluate emergent misalignment
  Research blog

2025

• TastyBench: Toward Measuring Research Taste in LLM
  Research blog
• Takes on Forbes article: “Fear Of Super Intelligent AI Is Driving Harvard And MIT Students To Drop Out”
  Commentary on a article I wad interviewed for
• It's (surprisingly) difficult to get college students to seriously think about AI.
  Thoughts on my university field building experience
• Lessons from a year of university AI safety field building
  Organizational update from Georgia Tech AISI
• College technical AI safety hackathon retrospective - Georgia Tech
  Reflection on hosting an AI alignment track at Georgia Tech's AI hackathon