OpenAI unveils new cyber model, claims it's less likely to hack companies

OpenAI unveiled its latest cybersecurity model GPT-6 Cyber, which it claimed is far more reliable staying within the boundaries researchers set. In an evaluation without deployment safety prompts, it avoided exploiting out-of-scope services in 99.93% of cases, up from 94.49% for GPT-5.6 Cyber. With the prompts, GPT-6 Cyber stayed within bounds 100% of the time.