Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Distillation for Incrimination and Distillation for Capabilities
Sebastian Prasanna, Jacqueline Tay, Alek Westover
Powerful misaligned AI models might recognize alignment evaluations and strategically behave well on them, rendering direct audits uninformative. However, distilling such a model i…
cs.DS2026
Lower Bounds for Linear Hashing via Arithmetic Kakeya
Ainesh Bakshi, Alex Conway, Hanna Komlós +2
Affine modular linear hashing is one of the simplest classical hash families. For a prime , the hash function is obtained by choosing uniformly from and…