superego
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values
Watson, Nell, Amer, Ahmed, Harris, Evan, Ravindra, Preeti, Zhang, Shujun
Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values, complex safety requirements, and specific compliance needs. Existing alignment methodologies often falter when faced with the complex task of providing personalized context without inducing confabulation or operational inefficiencies. This paper introduces a novel solution: a 'superego' agent, designed as a personalized oversight mechanism for agentic AI. This system dynamically steers AI planning by referencing user-selected 'Creed Constitutions' encapsulating diverse rule sets -- with adjustable adherence levels to fit non-negotiable values. A real-time compliance enforcer validates plans against these constitutions and a universal ethical floor before execution. We present a functional system, including a demonstration interface with a prototypical constitution-sharing portal, and successful integration with third-party models via the Model Context Protocol (MCP). Comprehensive benchmark evaluations (HarmBench, AgentHarm) demonstrate that our Superego agent dramatically reduces harmful outputs -- achieving up to a 98.3% harm score reduction and near-perfect refusal rates (e.g., 100% with Claude Sonnet 4 on AgentHarm's harmful set) for leading LLMs like Gemini 2.5 Flash and GPT-4o. This approach substantially simplifies personalized AI alignment, rendering agentic systems more reliably attuned to individual and cultural contexts, while also enabling substantial safety improvements. An overview on this research with examples is available at https://superego.creed.space.
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.14)
- Europe > Austria > Vienna (0.14)
- (3 more...)
- Law (1.00)
- Information Technology > Security & Privacy (1.00)
- Education (1.00)
- Health & Medicine > Therapeutic Area > Neurology (0.67)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Chatbot (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Artificial Intelligence - Muse And Poet
This snowball effect would lead to an intelligence explosion yielding a superintelligence surpassing all human control, understanding and comprehension. In other words, once we learn how to make machines that can reprogram themselves autonomously and are of course self-aware, they will reach the near infinite nigh-omniscience of the Technological Singularity. Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an'intelligence explosion,' and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make, provided that the machine is docile enough to tell us how to keep it under control.