Search Results for author:
Found 5 papers, 1 papers with code
Demanding and Designing Aligned Cognitive Architectures
To support this move, we define several AI cognitive architectures that combine reward maximization with other technical elements designed to improve alignment.
ML Agent Safety Mechanisms based on Counterfactual Planning
The key step in counterfactual planning is to use the agent's machine learning system to construct a counterfactual world model, designed to be different from the real world the agent is in.
Counterfactual Planning in AGI Systems
The key step in counterfactual planning is to use an AGI machine learning system to construct a counterfactual world model, designed to be different from the real world the system is in.
AGI Agent Safety by Iteratively Improving the Utility Function
We present an AGI safety layer that creates a special dedicated input terminal to support the iterative improvement of an AGI agent's utility function.
Corrigibility with Utility Preservation
The results in this paper were obtained by concurrently developing an AGI agent simulator, an agent model, and proofs.
