GPT-5.1-Codex-Max System Card
Must ReadOpenAI Blog · 2025-11-19 00:00 UTC AI
AI Summary
The article describes safety measures for GPT‑5.1‑CodexMax. It includes model‑level mitigations like specialized safety training for harmful tasks and prompt injections. It also outlines product‑level mitigations such as agent sandboxing and configurable network access.
AI analysis by Groq
Why should I care?
Because the reader is interested in AI, LLMs, AI Agents, and AI Model releases, this article informs them about new safety features in a cutting‑edge model.
Content
This system card outlines the comprehensive safety measures implemented for GPT‑5.1-CodexMax. It details both model-level mitigations, such as specialized safety training for harmful tasks and prompt injections, and product-level mitigations like agent sandboxing and configurable network access.