Models
OpenAI strengthens safeguards against GPT-6.2 reasoning extraction
OpenAI says it has significantly strengthened safeguards against extracting internal reasoning from its GPT-6.2 Astra and GPT-6.2 Sol models. In adaptive red-teaming tests, the success rate for extracting protected reasoning fell from 54% to 0.2%, according to the report. OpenAI is also suspending thousands to tens of thousands of accounts each week over coordinated distillation campaigns.
OpenAImodel securityreasoning extraction