Beyond Capabilities: A Framework for Integrating Moral Patiency Indicators into AI Forecasting and Governance
Maximus Rafla
Submitted to The AI Forecasting Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
Current AI forecasting focuses almost exclusively on capabilities and timelines, creating a dangerous blind spot for the potential emergence of moral patiency (e.g., sentience). This represents a critical governance failure, as an AI's moral status is a far more significant societal "branching point" than its task performance. Our project addresses this gap by proposing a novel, two-part framework. The first component is a proactive "dashboard" of early-warning indicators—drawing from behavioral science, computational neuroscience, and information theory—to begin monitoring for signals of moral patiency in frontier models. The second component is a tiered governance response system that links the detection of these indicators to specific, pre-planned policy actions, such as mandatory audits or training pauses. This framework transforms an abstract philosophical debate into a concrete, actionable problem of risk management, providing a vital tool for proactive and responsible AI governance.
Reviews
No public critique yet.
Cite this project
@misc{rafla2025beyond,
title = {{Beyond Capabilities: A Framework for Integrating Moral Patiency Indicators into AI Forecasting and Governance}},
author = {Maximus Rafla},
year = {2025},
month = nov,
note = {Submitted to The AI Forecasting Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/beyond-capabilities-a-framework-for-integrating-moral-patiency-indicators-into-ai-forecasting-and-governance-cvuy}},
url = {https://apartresearch.com/sprints/projects/beyond-capabilities-a-framework-for-integrating-moral-patiency-indicators-into-ai-forecasting-and-governance-cvuy}
}More from The AI Forecasting Hackathon
- View project: System Dynamics Game-Theoretic Model of the AI Development Race
System Dynamics Game-Theoretic Model of the AI Development Race
System Dynamics BCN
A Game theoretic / System Dynamics model of the race dynamics of the US, China, and EU, as a follow up to the Armstrong et al. (2016) paper “Racing to the Precipice”. We find preliminary results where knowledge of …
- View project: ExogenousAI
ExogenousAI
Fibonacci
Current AI capability forecasting methodologies, including EpochAI's Direct Approach and Biological Anchors framework, primarily rely on internal metrics such as training compute and scaling laws while assuming stable …
- View project: AI Incidents Forecasting
AI Incidents Forecasting
KLACE
This research develops a framework for forecasting AI incidents to help predict future risks. We have developed two models that forecasts incidents which include calibrated 90% prediction intervals with backtests. These …