ai-fail-safe
Popular repositories
-
safe-reward
safe-reward Publica prototype for an AI safety library that allows an agent to maximize its reward by solving a puzzle in order to prevent the worst-case outcomes of perverse instantiation
Python 8
-
gene-drive
gene-drive Publica project to ensure that all child processes created by an agent "inherit" the agent's safety controls
Repositories
Showing 5 of 5 repositories
- safe-reward Public
a prototype for an AI safety library that allows an agent to maximize its reward by solving a puzzle in order to prevent the worst-case outcomes of perverse instantiation
- gene-drive Public
a project to ensure that all child processes created by an agent "inherit" the agent's safety controls