# TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI

arXiv: https://arxiv.org/abs/2306.06924 · HTML: https://mlsanity.com/paper/2306.06924/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 64 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 13 of 13)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Conservative Agency via Attainable Utility Preservation](https://mlsanity.com/paper/1902.09725/) (2019)
- [Preferences Implicit in the State of the World](https://mlsanity.com/paper/1902.04198/) (2019)
- [Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning](https://mlsanity.com/paper/1903.08542/) (2019)
- [Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning](https://mlsanity.com/paper/1903.03877/) (2019)
- [Low Impact Artificial Intelligences](https://mlsanity.com/paper/1705.10720/) (2017)
- [Incorrigibility in the CIRL Framework](https://mlsanity.com/paper/1709.06275/) (2017)
- [Taxonomy of Pathways to Dangerous AI](https://mlsanity.com/paper/1511.03246/) (2015)
- [Servant of Many Masters: Shifting priorities in Pareto-optimal sequential decision-making](https://mlsanity.com/paper/1711.00363/) (2017)
- [Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making](https://mlsanity.com/paper/1701.01302/) (2017)

## Built on by (most cited first, 26 of 26)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Sabotage Evaluations for Frontier Models](https://mlsanity.com/paper/2410.21514/) (2024)
- [From task structures to world models: What do LLMs know?](https://mlsanity.com/paper/2310.04276/) (2023)
- [A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms](https://mlsanity.com/paper/2407.01294/) (2024)
- [Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators](https://mlsanity.com/paper/2402.01708/) (2024)
- [The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence](https://mlsanity.com/paper/2408.12622/) (2024)
- [An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI](https://mlsanity.com/paper/2310.14455/) (2023)
- [A Framework for Responsible AI Systems: Building Societal Trust through Domain Definition, Trustworthy AI Design, Auditability, Accountability, and Governance](https://mlsanity.com/paper/2503.04739/) (2025)
- [Avoiding Catastrophe in Online Learning by Asking for Help](https://mlsanity.com/paper/2402.08062/) (2024)
- [Misalignment or misuse? The AGI alignment tradeoff](https://mlsanity.com/paper/2506.03755/) (2025)
- [Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond](https://mlsanity.com/paper/2607.02197/) (2026)
- [Strategic Insights from Simulation Gaming of AI Race Dynamics](https://mlsanity.com/paper/2410.03092/) (2024)
- [TechOps: Technical Documentation Templates for the AI Act](https://mlsanity.com/paper/2508.08804/) (2025)
- [AI Finds A Way](https://mlsanity.com/paper/2608.23875/) (2026)
- [The Economics of p(doom): Scenarios of Existential Risk and Economic Growth in the Age of Transformative AI](https://mlsanity.com/paper/2503.07341/) (2025)
- [Against racing to AGI: Cooperation, deterrence, and catastrophic risks](https://mlsanity.com/paper/2507.21839/) (2025)
- [General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance](https://mlsanity.com/paper/2307.14283/) (2023)
- [Taxonomy to Regulation: A (Geo)Political Taxonomy for AI Risks and Regulatory Measures in the EU AI Act](https://mlsanity.com/paper/2404.11476/) (2024)
- [Safe Learning Under Irreversible Dynamics via Asking for Help](https://mlsanity.com/paper/2502.14043/) (2025)
- [Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks](https://mlsanity.com/paper/2508.06411/) (2025)
- [A Taxonomy of Omnicidal Futures Involving Artificial Intelligence](https://mlsanity.com/paper/2507.09369/) (2025)
- [AI Consciousness and Existential Risk](https://mlsanity.com/paper/2511.19115/) (2025)
- [Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem](https://mlsanity.com/paper/2604.20805/) (2026)
- [Culturally Situated AI Safety for Youth: Saudi Arabian Perspectives of Youth, Parents and Teachers](https://mlsanity.com/paper/2604.26494/) (2026)

## Abstract (arXiv)

While several recent works have identified societal-scale and extinction-level risks to humanity arising from artificial intelligence, few have attempted an em exhaustive taxonomy of such risks. Many exhaustive taxonomies are possible, and some are useful -- particularly if they reveal new risks or practical approaches to safety. This paper explores a taxonomy based on accountability: whose actions lead to the risk, are the actors unified, and are they deliberate? We also provide stories to illustrate how the various risk types could each play out, including risks arising from unanticipated interactions of many AI systems, as well as risks from deliberate misuse, for which combined technical and policy solutions are indicated.