Rico Angell(@rico_angell):It’s deployment time! You’ve done the pre-deployment evals. You THINK your model is safe, so you ship it 🚀 🚨 After deployment, reports of misbehavior start trickling in What happened?? How could you have caught it?? 🤔 @icmlconf 2026 Spotlight! 🧵

Rico Angell

@rico_angell

AI Safety Researcher. Postdoc at NYU CDS.

参加 September 2024

314 フォロー中 146 ファン

Rico Angell@rico_angell

2026.05.14 19:31

It’s deployment time! You’ve done the pre-deployment evals. You THINK your model is safe, so you ship it 🚀 🚨 After deployment, reports of misbehavior start trickling in What happened?? How could you have caught it?? 🤔 @icmlconf 2026 Spotlight! 🧵