OfficialNov 20, 2026 ·
Combatting adversarial distillation
OpenAI’s layered approach to adversarial distillation combines model training, safeguards, detection, and enforcement to protect against capability extraction.
Published
Nov 20, 2026
Source
OpenAI
Daily digest
The day's biggest AI news in one short email, every morning. Plus an instant heads-up when a reset or a big release lands.
More on OpenAI
- Nov 20Meet the Data Agent in ChatGPTOfficial video
- Nov 20Codex CLI 0.171.0 is outUpdate
- Nov 20Hebbia sees improvements in financial research with GPT-6 AstraOfficial
- Nov 19Today in 2025 (3/7): @Theo rightfully pointed out that model names had lost the plot as "gpt-5.1-codex-max" was releasedOfficial
- Nov 19Introducing Higgsfield GPU Harness.Official
- Nov 19Explore the Codex Security PluginOfficial