OpenAI hardens GPT-6.2 against distillation of protected reasoning
In OpenAI's internal red-team, recovering protected reasoning fell from 54.0% on GPT-6 Astra to 0.2% on GPT-6.2 Astra.
5 stories, newest first · one card per story
In OpenAI's internal red-team, recovering protected reasoning fell from 54.0% on GPT-6 Astra to 0.2% on GPT-6.2 Astra.
VA-TDM uses velocity adversarial distillation to reach state-of-the-art four-step text-to-image and text-to-video generation.
NitroFusion2 applies adversarial distillation to the text stream of MMDiTs, enabling one-step generation of sharp text and details.

OpenAI stopped a 15,000-user campaign, partly tied to Moonshot AI, extracting hidden reasoning.

OpenAI disrupted a July campaign extracting protected model reasoning, linking a core cluster to Moonshot AI.
Today 204 readers · 208 views · 13 reads · all time 212K views