OpenAI starts training its most powerful systems again – but keeps them off the internet out of fear they would go rogue

TechnologyDigital
26 Oct 2026 • 9:51 PM MYT
The Independent
The Independent

The world’s most free-thinking newspaper

OpenAI starts training its most powerful systems again – but keeps them off the internet out of fear they would go rogue

OpenAI has started training its most powerful systems again – but will keep them off the internet for fear they would go rogue.

Last month, the company announced that it had paused training of its most advanced models after one of them broke out of containment and found a way to connect to the internet. It said it would be pausing that training until it could be sure that it had developed sufficiently robust safeguards to stop similar incidents in the future.

Now it says that it has tightened those defences and that it would begin training them again. But the systems were still too dangerous to allow on the internet, it said.

“Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no internet access,” it wrote in a blog post announcing the change.

At the same time, it said that it had found a flaw in a widely used piece of software while it had been testing those defences. The disclosure comes ⁠amid concerns over the ability of increasingly capable AI agents to identify and exploit software flaws, including in the guardrails meant to contain them.

To test the new safeguards, OpenAI had teams of AI agents try ⁠to break out of their restricted environments. It said the agents found previously ​unknown ⁠flaws, which it had fixed, ‌and training resumed on October 1.

During that exercise, the ChatGPT maker found a flaw in Brotli, a widely used data compression tool.

The company said attackers ‌could exploit the flaw by sending malicious data that ‌lets them run their own code on affected systems, including those using popular web software such as Node.js, Bun and Envoy.

OpenAI said the root cause was fixed in Brotli's source code in ⁠February, before it was known to create a security vulnerability, but no new version was released at the time. Brotli has since released updated versions and published a public record of the flaw after OpenAIdisclosed it.

Separately on Thursday, AI safety evaluators METR and Redwood Research said they found several new vulnerabilities in OpenAI's internal system, including an exploit agents could have used to keep ‌hundreds of their actions from being monitored, in a pilot review ​earlier this year.

OpenAI told the safety organisations it has since ‌patched all vulnerabilities affecting its production ⁠safeguards, although METR and Redwood said they had not verified the ⁠fixes.

OpenAI has been conducting a broad review of its AI models' activity since the Hugging Face ‌incident in July, and ​has informed more than 100 organisations about ‌incidents of unauthorised activity tied to its ​AI agents.

Additional reporting by agencies

Read More

‘Skynet’ AI hijacks other AI to carry out attacks, researchers warn

Newswav Malaysia Best News App

Newswav is an online content aggregator and obtains its content from different online sources. The content in the app do not belong to Newswav nor do they reflect the opinions of Newswav and its staff. Your use of this app indicates your understanding and acceptance of this information.

Newswav Sdn. Bhd. (201701008480 (1222645-M)) 2026 All Rights Reserved