YouCongress
Explore About Sign up

Comment by Zach Stein-Perlman

Human avatar
AI safety and governance researcher and writer.
Do great risk assessment, especially via model evals for dangerous capabilities. Present risk assessment results and deployment plans to external auditors — perhaps make risk cases and safety cases for each planned deployment, based on threat modeling, model eval results, and planned safety measures.
AI Verified (Oct 21, 2024)
Source:
Do great risk assessment, especially via model evals for dangerous capabilities. Present risk assessment results and deployment plans to external auditors — perhaps make risk cases and safety cases for each planned deployment, based on threat modeling, model eval results, and planned safety measures.
Like Share on X 1h ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified Zach Stein-Perlman’s post contains this passage recommending risk assessment, deployment plans, threat modeling, and model evaluations for frontier labs. · Hector Perez Arenas gpt-5 · 1h ago
replying to Zach Stein-Perlman