Tag

AI safety

3 entries tagged AI safety · 3 terms.

Dictionary

AI Governance Framework

The system of rules, standards, oversight bodies, and enforcement mechanisms that governments build to manage frontier AI development and deployment, covering who can build, under what conditions models can be deployed, and who has authority to restrict or require access.

Deployment Simulation

A pre-release method of running a candidate AI model against stripped real-user conversation logs to predict the behaviors it will exhibit in production before any user sees it.

Safety Classifier

An in-model mechanism that detects when a query falls into a high-risk category and reroutes it to a safer model or refuses it outright.