The AI Alignment Paradox
The better we align AI models with our values, the easier we may make it to realign them with opposing values.
Authors
- Roland Can Aydin (ORCID: https://orcid.org/0000-0002-9542-9146)
- Robert West (ORCID: https://orcid.org/0000-0002-3984-1232)
Institutions
- Universität Hamburg (DE)
- École Polytechnique Fédérale de Lausanne (CH)
- Hamburg University of Technology (DE)
Publication Details
- Journal
- Communications of the ACM
- Published
- 2025-02-05
- DOI
- https://doi.org/10.1145/3705294
- Citations
- 7
- Primary Topic
- Ethics and Social Impacts of AI
- Type
- article
- Field-Weighted Citation Impact
- 16.56