Skip to main content
See every side of every news story
Published • loading... • Updated

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

Summary by TokenPost
Internal automated testing measured attempts to recover protected reasoning traces in GPT-6 Astra and GPT-6.2 Astra.
DisclaimerThis story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.

5 Articles

OpenAI massively strengthens the protection of internal thinking processes at GPT-6.2 Astra and GPT-6.2 Sol. In adaptive red-teaming tests, the success rate for reading protected thought processes dropped from 54 to 0.2 percent. At the same time, the company blocks thousands to tens of thousands of accounts per week that are involved in coordinated distillation campaigns. The article AI-Datenklau: OpenAI makes imitators' models hard to live appe…

·Germany
Read Full Article

The company claims that its new defenses reduced the effectiveness of certain protected reasoning extraction attacks from 54% to 0.2%. It also requests measures The post OpenAI claims to reduce 99.6% attacks to extract GPT-6.2 reasoning and calls for sanctions against foreign actors appeared first on .

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • There is no tracked Bias information for the sources covering this story.

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

TokenPost broke the news on Friday, November 20, 2026.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal