Back to news

AI · Article

OpenAI Sharply Cuts Success of Attacks on GPT-6.2 Astra and Sol Reasoning

The Decoder ·

At a glance

OpenAI has greatly strengthened its defenses against attempts to pull the hidden reasoning out of its latest models, GPT-6.2 Astra and GPT-6.2 Sol. In its own internal tests, the success rate of these attacks fell sharply, and OpenAI says it is now bringing some of these improvements to GPT-6 Astra too.

Key points

Why it matters

Hidden reasoning is a core part of how AI models work, and copying it can let rivals build similar systems. Stronger protection makes that theft harder.

Original source

OpenAI makes it much harder for attackers to extract how its latest AI models think

The Decoder · Nov 21, 05:31 KST

Read on The Decoder ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to The Decoder.

AI