Research
OpenAI is now using AI to attack its own AI， and it's working better than humans ever did
OpenAI 用 AI 攻击自家 AI：GPT-Red 自动发现安全漏洞，成功率 84% 远超人类
OpenAI is now using AI to attack its own AI, and it's working better than humans ever did
The DecoderOpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed directly into hardening models like GPT-5.6 Sol.
Open sourceRecommended because
This is worth tracking because it is a concrete research signal, not just a passing headline. The source preview points to a research result, method, evaluation, dataset, or safety finding. For builders and operators, "OpenAI is now using AI to attack its own AI， and it's working better than humans ever did" can be used as a checkpoint for technical due diligence, roadmap bets, agent design, and evaluation strategy. I keep this thread indexed so future searches around AI research papers, technical methods, and applied AI systems can land on a source-linked page instead of disappearing into a fast-moving feed from The Decoder.
What to take from this signal
Context
"OpenAI is now using AI to attack its own AI， and it's working better than humans ever did" is archived here as a source-linked AI signal from The Decoder. The useful part is the connection between OpenAI, attack, own, working, better and technical due diligence, roadmap bets, agent design, and evaluation strategy, which makes the item more actionable than a normal feed headline. The source context says: OpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed directly into hardening models like GPT-5.6 Sol.
Builder takeaway
For an AI builder, the main takeaway is to watch how this signal changes practical decisions around technical feasibility, evaluation design, safety limits, and product primitives. It can inform what to test next, which product surface to compare, and whether the underlying workflow is ready for real users.
Source context
The Decoder remains the authoritative source for the original claim. This page adds a stable archive URL, a short builder interpretation, and related search language so the item can be found later when the original feed has moved on.
Search angles
- OpenAI is now using AI to attack its own AI， and it's working better than humans ever did Research context
- The Decoder AI research
- OpenAI, attack, own, working, better builder takeaway
- AI research papers, technical methods, and applied AI systems
This page keeps a source preview and a stable archive URL for search discovery. The original source remains authoritative.