by Kyle Alspach, via CRN

A key emerging lesson from the attack carried out by rogue OpenAI models is that, going forward, evaluation of frontier models may need to take place within a fully cordoned off testing environment, cybersecurity experts told CRN.

For AI models with the most powerful cyber capabilities, standard network restrictions meant to prevent internet access may no longer be sufficient, given that OpenAI's agents were able to bypass those controls, experts said.

Meeting The Need For Safe Testing

The center now enables customers to test advanced AI models—including LLM-powered offensive security tools—in addition to other new capabilities, said Konrad, vice president of global cyber at St. Louis-based WWT, No. 10 on CRN's Solution Provider 500 for 2026.

 

Read full article