Skip to content

GPT-5.1

Named by 2 kept items in this workspace.

1 items name it under affected products and 1 under tools.

The items that name it 2

  • AI Security Briefing
    repoas tools2026-07-19

    Compared as a baseline on Text Query and Text Response content safety benchmarks

  • AI Security Briefing
    articleas affected products2026-07-18It is written here as GPT-5.1 (target of GPT-Red; "Fake Chain-of-Thought" attacks achieved success rates upwards of 95%).

    target of GPT-Red; "Fake Chain-of-Thought" attacks achieved success rates upwards of 95%

In every workspace you can read 6

Security

All technologies in this workspace.