
SecurityLead story
OpenAI built GPT-Red, an LLM super-hacker, to harden its own models
The internal red-team model cut successful attack rates from over 90% on GPT-5 to under 23% on the new GPT-5.6.
Jaeden SchaferEditor in Chief5 min read
Tag · 1 story
Every story tagged GPT-Red on AI Chat Daily.

The internal red-team model cut successful attack rates from over 90% on GPT-5 to under 23% on the new GPT-5.6.
The tightly edited AI news email engineers, founders, and investors actually open. One email. Every weekday. Five minutes to finish.
The briefing read inside teams at