Rico Angell
@rico_angell
AI Safety Researcher. Postdoc at NYU CDS.
๊ฐ์
September 2024
314 ํ๋ก์ ์ค 146 ํฌ
Itโs deployment time!
Youโve done the pre-deployment evals. You THINK your model is safe, so you ship it ๐
๐จ After deployment, reports of misbehavior start trickling in
What happened?? How could you have caught it?? ๐ค
@icmlconf 2026 Spotlight!
๐งต
๋ ๋ณด๊ธฐ
