# Concrete Problems in AI Safety, Revisited

arXiv: https://arxiv.org/abs/2401.10899 · HTML: https://mlsanity.com/paper/2401.10899/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Show Your Work: Improved Reporting of Experimental Results](https://mlsanity.com/paper/1909.03004/) (2019)
- [A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems](https://mlsanity.com/paper/1705.01292/) (2017)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing](https://mlsanity.com/paper/2001.00964/) (2020)
- [Engineering Safety in Machine Learning](https://mlsanity.com/paper/1601.04126/) (2016)
- [Robot Rights? Let's Talk about Human Welfare Instead](https://mlsanity.com/paper/2001.05046/) (2020)

## Built on by (most cited first, 22 of 22)

- [LLM-based NLG Evaluation: Current Status and Challenges](https://mlsanity.com/paper/2402.01383/) (2024)
- [Toward an Evaluation Science for Generative AI Systems](https://mlsanity.com/paper/2503.05336/) (2025)
- [Preference Tuning For Toxicity Mitigation Generalizes Across Languages](https://mlsanity.com/paper/2406.16235/) (2024)
- [Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects](https://mlsanity.com/paper/2505.18893/) (2025)
- [AI Risk Management Should Incorporate Both Safety and Security](https://mlsanity.com/paper/2405.19524/) (2024)
- [The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources](https://mlsanity.com/paper/2406.16746/) (2024)
- [AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations](https://mlsanity.com/paper/2406.18346/) (2024)
- [Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models](https://mlsanity.com/paper/2507.13383/) (2025)
- [AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security](https://mlsanity.com/paper/2504.20965/) (2025)
- [Aligning Large Language Models from Self-Reference AI Feedback with one General Principle](https://mlsanity.com/paper/2406.11190/) (2024)
- [MCP-AI: Protocol-Driven Intelligence Framework for Autonomous Reasoning in Healthcare](https://mlsanity.com/paper/2512.05365/) (2025)
- [Risk-Calibrated Learning: Minimizing Fatal Errors in Medical AI](https://mlsanity.com/paper/2604.12693/) (2026)
- [Preliminary Quantitative Study on Explainability and Trust in AI Systems](https://mlsanity.com/paper/2510.15769/) (2025)
- [How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape](https://mlsanity.com/paper/2601.06033/) (2025)
- [Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem](https://mlsanity.com/paper/2604.20805/) (2026)
- [Improving Model Safety by Targeted Error Correction](https://mlsanity.com/paper/2605.02544/) (2026)
- [StepGuard: Guarding Web Navigation via Single-Step Calibration](https://mlsanity.com/paper/2606.17871/) (2026)
- [Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI](https://mlsanity.com/paper/2607.14353/) (2026)
- [Toward a Theory of Value in AI Alignment](https://mlsanity.com/paper/2608.10327/) (2026)
- [Co-constructing sociotechnical AI governance: participatory system mapping using algorithm registers](https://mlsanity.com/paper/2608.12166/) (2026)
- [Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery](https://mlsanity.com/paper/2609.18460/) (2026)
- [The Ethics of Artificial Intelligence in Military Operations](https://mlsanity.com/paper/2609.26507/) (2026)

## Abstract (arXiv)

As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real life.