Openai trained an ai for red teaming ai – Breaking News & Latest Updates 2026
Skip to main content
The homepageThe VergeThe Verge logo.
The homepageThe VergeThe Verge logo.
Posted
E
External Link
Emma Roth
OpenAI trained an AI for red-teaming AI.

The new GPT-Red model “can break nearly all models it is pitted against,” according to an OpenAI blog post on Wednesday. OpenAI says it used GPT-Red to find vulnerabilities in GPT-5.6 Sol, a process that made it the company’s “most robust model to prompt injections to date.”

Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Comments
Loading comments
Getting the conversation ready...

Most Popular

Most Popular
  1. The Light Flip is a minimalist flip phone with a point to prove
  2. The FCC is planning to retroactively ban disguised DJI gadgets
  3. Apple’s rumored ‘Upgrade’ program brings lease-to-own pricing for iPhones, Macs, and iPads
  4. Neill Blomkamp’s new zombie AI ‘film’ is just slop warmed over
  5. Samsung’s wider Z Fold 8 feels just right

More in AI

AMD commits up to $5 billion to AnthropicAMD commits up to $5 billion to Anthropic
Meta made its own AI detection system. It should have just used Google’sMeta made its own AI detection system. It should have just used Google’s
Utility companies promise to spare us from AI’s energy billUtility companies promise to spare us from AI’s energy bill
Neill Blomkamp’s new zombie AI ‘film’ is just slop warmed overNeill Blomkamp’s new zombie AI ‘film’ is just slop warmed over
OpenAI says it accidentally hacked Hugging Face with a new AI systemOpenAI says it accidentally hacked Hugging Face with a new AI system
Substack adds an AI detector to help spot blogs written by no oneSubstack adds an AI detector to help spot blogs written by no one

Top Stories