OpenAI published research on November 20, 2026 warning that distillation can reproduce powerful AI capabilities while bypassing the safety measures built into source models, and described a layered defense combining model training, safeguards, detection, and enforcement.
OpenAI said the findings are intended to sharpen its own defenses and support safeguards across the industry, against a backdrop Reuters described as a significant US-China geopolitical flashpoint over Chinese entities training domestic rivals by distilling US AI models.