Skip to content
The Nexus
DossierENTITY

GPT-Red

Coverage of GPT-Red in the Nexus archive.

Earliest in view: Jul 16 · 08:42 UTCMost recent: Jul 16 · 12:10 UTC
Co-mentioned in this coverage
Recent coverage
  • TECHNOLOGYJul 16 · 12:10 UTCMIT TECHNOLOGY REVIEW
    The Download: OpenAI unveils GPT-Red and heat pumps rise in the US

    OpenAI introduced GPT-Red, an AI model designed to enhance cybersecurity by automating red-teaming evaluations. Heat pump sales in the US have doubled over the past 15 years, outpacing natural-gas furnaces despite the recent expiration of a key tax credit.

  • TECHNOLOGYJul 16 · 08:42 UTCTHE HACKER NEWS
    OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

    OpenAI has developed GPT-Red, an automated red-teaming model designed to identify prompt injection vulnerabilities in its AI systems, including GPT-5.6 Sol. The model is used to adversarially train and harden AI tools before widespread deployment, addressing security weaknesses in previous models.

GPT-Red · Dossier · The Nexus