Tim Hua 🇺🇦(@Tim_Hua_):New Post: Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face. We focus on two goals: Understanding this incident, and evaluating for other misaligned tendencies. In this screenshot, we share our top five ideas. (Written in my personal capacity)

Tim Hua 🇺🇦

@Tim_Hua_

AI safety, Econ, new liberalism, math, and a bit of art history (as a treat) Member of Technical Staff @METR_Evals. Previously on Walmart’s economics team.

加入 December 2014

1.5K 正在關注 2.4K 粉絲

Tim Hua 🇺🇦@Tim_Hua_

2026.08.03 16:39

New Post: Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face. We focus on two goals: Understanding this incident, and evaluating for other misaligned tendencies. In this screenshot, we share our top five ideas. (Written in my personal capacity)