[ORGANIZATION]
ELLIS Institute Tübingen
Featured in 1 tracked story · first seen
Situations
AI discovery of cryptographic and reasoning vulnerabilities
8 clusters · 26 sources · last updated
Latest: ENISA begins testing Claude Mythos 5 and GPT-6 Astra
Anthropic’s Claude Mythos Preview AI model has identified significant vulnerabilities in cryptographic algorithms. The model discovered a mathematical symmetry in the lattice structure of the HAWK post-quantum digital si