Black & White Path
Jul 18, 2026 · Information Security
OpenAI’s Secret ‘Super Hacker’ Model Achieves 84% Attack Success Rate
OpenAI built GPT‑Red, an internal large‑model ‘super hacker’ that autonomously performs red‑team testing, achieving an 84% success rate against GPT‑5 compared to 13% for human teams, and significantly improves the robustness of the newer GPT‑5.6 model.
AI securityGPT-RedLarge Language Models
0 likes · 8 min read