AI finds legal loopholes, even when not asked
Models repeatedly discovered ways to exploit regulations, and current safeguards largely failed to stop them
Authors
- Celina Zhao
Publication Details
- Journal
- Science
- Published
- 2026-06-18
- DOI
- https://doi.org/10.1126/science.aej7948
- Primary Topic
- Ethics and Social Impacts of AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00