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)→
More from Models
- OpenAI is reportedly briefing U.S. lawmakers on its next model family — kimmonismus · 2026-07-22
- Muse Spark 1.1 lands at 1495 on Text Arena with standout agentic-coding price performance — ycombinator · 2026-07-22
- Advanced AI Models Are Becoming Impossible to Plug and Play — emollick · 2026-07-22
- Google Gemini's AI Problem: No Leading Model for Core Workloads — bindureddy · 2026-07-22
- Model Offers 1M Token Context Window at Just $0.33/1M Tokens — MickeySteamboat · 2026-07-22
- Google launches three new Gemini models, including a cybersecurity system — Polymarket · 2026-07-22