Anthropic reports new safeguards cut Claude distillation attacks by 90-99%

Anthropic stated that new multi-layered defenses, including preserved thinking restrictions, constitutional classifiers and rapid account bans, have reduced reasoning tokens extracted in distillation attacks by roughly 90% to 99%. The company cited Chinese developer Zhipu (Z.ai) as an example of attempted distillation linked to its GLM-5.3 model and warned of associated safety and national-security risks. The measures aim to hinder large-scale capability copying by rivals.