---
title: "OpenAI cuts reasoning-extraction attacks on GPT-6.2 from 54% to 0.2%"
url: https://www.parallelquant.com/posts/openai-cuts-reasoning-extraction-attacks-on-gpt-6-2-from-54-to-0-2-3ed45a
source_name: "The Decoder"
source_url: https://the-decoder.com/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models-think/
published: 2026-11-20T20:31:50.000Z
topics: ["security", "llms"]
publisher: "Parallel Quant"
---

# OpenAI cuts reasoning-extraction attacks on GPT-6.2 from 54% to 0.2%

*2026-11-20 · Source: [The Decoder](https://the-decoder.com/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models-think/)*

OpenAI says new safeguards make it far harder to extract the hidden reasoning of GPT-6.2 Astra and Sol; in adaptive red-team tests, extraction success dropped from 54% to 0.2%. The company also says it suspends thousands to tens of thousands of accounts each week over coordinated distillation campaigns.

**Why it matters:** Hidden chains of thought are now treated as core intellectual property, because rivals can distill them to train cheaper models. The account-suspension numbers show distillation has become an industrial-scale threat, especially as GPT-6.2's cheaper API pricing makes bulk querying more economical. Expect other labs to follow with similar defenses, which also reduces how much outside researchers can inspect model reasoning.

**Topics:** security, llms

---
Read the original: https://the-decoder.com/openai-makes-it-much-harder-for-attackers-to-extract-how-its-latest-ai-models-think/
Canonical: https://www.parallelquant.com/posts/openai-cuts-reasoning-extraction-attacks-on-gpt-6-2-from-54-to-0-2-3ed45a
Published by Parallel Quant — https://www.parallelquant.com
