The Fantasia Bound on Constitutional Classifiers: Thermodynamic Limits of Jailbreak Defence
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Anthropic's constitutional classifiers (2026) withstood 3,000+ hours of red teaming with no universal jailbreak. We derive a thermodynamic upper bound on classifier effectiveness from the Fantasia Bound I(D;Y)+I(M;Y)≤H(Y). A classifier is a prohibition mechanism: its channel capacity sets the maximum Pe it can suppress. We prove that no single-channel classifier can defend against attacks above a critical Pe threshold Pe_c = exp(C/kT) where C is the classifier's information capacity. The prohibition-ritual pair architecture (two independent channels) raises the bound but does not eliminate it. Constitutional classifiers succeed because they approximate the two-channel architecture — the constitution provides the ritual (explicit reasoning about refusal), while the classifier provides the prohibition. Predictions: universal jailbreaks exist above Pe_c; defence requires increasing channel capacity, not classifier complexity.
Fields of Study & Subjects
Adversarial Robustness in Machine Learning
Ethics and Social Impacts of AI
Diverse Interdisciplinary Research Studies
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 27 March 2026
- Language
- EN
- Document type
- Preprint