Skip to content
Saturday, 21 November 2026
Tenesys AI News
Subscribe

GPT-6.2 Astra, GPT-6.2 Sol

Change history

  1. 20 Nov 2026
    New safeguards against adversarial model distillation
    ParameterBeforeNow
    Protected reasoning extraction success rate54.0% (GPT-6 Astra)0.2% (GPT-6.2 Astra)

News

Cyber Security· Important· 🧪 Worth Testing

New safeguards against adversarial model distillation

OpenAI has implemented enhanced security defenses to block 'adversarial distillation,' a technique where attackers attempt to extract a model's internal reasoning traces (chain-of-thought) to train unauthorized models. The update introduces tighter API-level controls, improved output classifiers, and better linkage between reasoning traces and specific conversation histories.

OpenAI
GPT-6.2 Astra, GPT-6.2 Sol · TENESYS AI NEWS