OpenAI shares new research on detecting and disrupting model distillation attempts

jdjohnson · x · 2026-11-21

OpenAI published new research on combating distillation of its models, showing how distilled capabilities can reproduce powerful AI abilities without the original safeguards.

The company describes how it detects capability transfer and disrupts coordinated distillation attempts, saying the findings are sharpening its defenses and supporting safeguards across the industry. The quote-tweet's comment ("I don't hate these companies enough") reflects developer frustration with vendors locking down distillation.

Related event: OpenAI Publishes Anti-Distillation Research(3 posts)→

Original post →

More from Models

Models channel →