OpenAI Red Team Model GPT-Red Far Surpasses Humans

kaicathyc · x · 2026-07-16

OpenAI researcher Kathy revealed the evolution of their infrastructure and algorithms, mentioning an internally codenamed model called GPT-Red. This model is specifically trained to discover system vulnerabilities and has already surpassed human expert levels in red teaming tests.

Related event: OpenAI unveils automated red-teaming system GPT-Red(16 posts)→

Original post →

More from Models

Models channel →