# OpenAI Says GPT-6.2 Astra Cut Reasoning Extraction Success to 0.2%

By Simon Yoon

Canonical URL: https://www.tokenpost.com/news/technology/62296
Published: 2026-11-20T19:53:24.000Z
Updated: 2026-11-20T19:53:24.000Z
Section: Technology

> Internal automated testing measured attempts to recover protected reasoning traces in GPT-6 Astra and GPT-6.2 Astra.

OpenAI’s internal evaluation using automated red-teaming found a 0.2% success rate for attempts to recover protected reasoning traces from GPT-6.2 Astra, compared with 54.0% for GPT-6 Astra with its original safeguards.

The company evaluated the models by testing whether attackers could recover protected reasoning traces. The comparison covered GPT-6 Astra with its original safeguards and GPT-6.2 Astra with updated protections.

OpenAI’s defenses combine adversarial testing, model training, classifiers, API protections and investigations into coordinated extraction attempts. The protections cover GPT-6.2 Astra and GPT-6.2 Sol, though no separate test result for Sol was provided.

Adversarial distillation uses the outputs of a capable model to train or reproduce another model. The practice poses particular risks in dual-use fields such as cybersecurity and biology, where a resulting system could lack the original model’s safeguards.

OpenAI disclosed a separate adversarial distillation campaign on Sept. 30, saying it had disrupted the activity by July 28. The company attributed a core cluster to people associated with Moonshot AI but said it could not establish that every operator belonged to one actor.


