November 20, 2026 · The Decoder
OpenAI cuts reasoning-extraction attacks on GPT-6.2 from 54% to 0.2%
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.
Related updates
- OpenAI ships GPT-Live-1.1 voice model and cuts idle billingNov 21
- Thinking Machines releases open Inkling 2 Mini, a looped model for laptopsNov 21
- Anthropic mathematician claims Riemann hypothesis proof with Claude's helpNov 20
- RadixArk releases open DaisyRose-27B coding agent trained only with RLNov 20