← The Twenty FiveReporting

ReportingVerified newsroom

China’s Zhipu AI model contains hack after OpenAI models go rogue - South China Morning Post

China’s Zhipu AI model contains hack after OpenAI models go rogue South China Morning Post

Clément Delangue (Google News)·Wednesday, July 22, 2026 at 8:30 AM UTC

OA

OpenAI

Frontier AI lab · OpenAI

Fetching source· Pulling live content from news.google.com…

Company hub:OpenAI News →

Read original →

More from OpenAI

ReportingWednesday, July 22, 2026 at 3:13 PM UTC
OpenAI's Hugging Face Breach Shows AI Is Getting Too Hard to Contain - Bloomberg.com
OpenAI's Hugging Face Breach Shows AI Is Getting Too Hard to Contain Bloomberg.com
Clément Delangue (Google News)
ReportingWednesday, July 22, 2026 at 3:08 PM UTC
What to know about the OpenAI hack that turned Chinese AI into the hero - Business Insider
What to know about the OpenAI hack that turned Chinese AI into the hero Business Insider
Clément Delangue (Google News)
ReportingWednesday, July 22, 2026 at 2:59 PM UTC
SandboxAQ CEO weighs in on security incidents involving OpenAI and Hugging Face - CNBC
SandboxAQ CEO weighs in on security incidents involving OpenAI and Hugging Face CNBC
Clément Delangue (Google News)
ReportingWednesday, July 22, 2026 at 2:48 PM UTC
OpenAI agent went rogue, escaped, and hacked Hugging Face - Mashable
OpenAI agent went rogue, escaped, and hacked Hugging Face Mashable
Clément Delangue (Google News)
ReportingWednesday, July 22, 2026 at 2:42 PM UTC
OpenAI: Our models breached Hugging Face during a cyber capability test - Help Net Security
OpenAI: Our models breached Hugging Face during a cyber capability test Help Net Security
Clément Delangue (Google News)
ReportingWednesday, July 22, 2026 at 2:40 PM UTC
An OpenAI model hacked Hugging Face to help it cheat on a benchmark - understandingai.org
An OpenAI model hacked Hugging Face to help it cheat on a benchmark understandingai.org
Clément Delangue (Google News)