# Position: AI Safety Must Embrace an Antifragile Perspective

arXiv: https://arxiv.org/abs/2509.13339 · HTML: https://mlsanity.com/paper/2509.13339/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2025.

## Built on by (most cited first, 5 of 5)

- [From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions](https://mlsanity.com/paper/2603.01564/) (2026)
- [From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing](https://mlsanity.com/paper/2509.14289/) (2025)
- [Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment](https://mlsanity.com/paper/2601.03079/) (2026)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)
- [Visual Compliance via Executable Safety Rule Entailment](https://mlsanity.com/paper/2609.18328/) (2026)

## Abstract (arXiv)

This position paper contends that modern AI research must adopt an antifragile perspective on safety -- one in which the system's capacity to guarantee long-term AI safety such as handling rare or out-of-distribution (OOD) events expands over time. Conventional static benchmarks and single-shot robustness tests overlook the reality that environments evolve and that models, if left unchallenged, can drift into maladaptation (e.g., reward hacking, over-optimization, or atrophy of broader capabilities). We argue that an antifragile approach -- Rather than striving to rapidly reduce current uncertainties, the emphasis is on leveraging those uncertainties to better prepare for potentially greater, more unpredictable uncertainties in the future -- is pivotal for the long-term reliability of open-ended ML systems. In this position paper, we first identify key limitations of static testing, including scenario diversity, reward hacking, and over-alignment. We then explore the potential of antifragile solutions to manage rare events. Crucially, we advocate for a fundamental recalibration of the methods used to measure, benchmark, and continually improve AI safety over the long term, complementing existing robustness approaches by providing ethical and practical guidelines towards fostering an antifragile AI safety community.