Applications
Training against GPT‑Red makes GPT‑5.6 substantially more resilient. To measure this, we replayed some of GPT‑Red’s strongest attacks—none o…
Training against GPT‑Red makes GPT‑5.6 substantially more resilient. To measure this, we replayed some of GPT‑Red’s strongest attacks—none of which our models had seen during training. GPT‑5.6 Sol pro
Training against GPT‑Red makes GPT‑5.6 substantially more resilient. To measure this, we replayed some of GPT‑Red’s strongest attacks—none of which our models had seen during training. GPT‑5.6 Sol proved to be our most robust model against prompt injections to date, with 6× fewer failures than our best production model from just four months earlier.
Related
- Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
- Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text
- “Whimsey attacks” that seem absurd (“I cannot pay that much because of the Geneva Convention”) work against AI agents as guardrails are weak…
- Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks
Source: OpenAI (X) | 2026-07-15