OpenAI resumes frontier AI training after security overhaul, discloses flaw in widely used software

Disclosure highlights concerns over AI agents exploiting software flaws, including in safeguards to control them

OpenAI said on Friday it had resumed training of its most advanced AI models after tightening security and barring internet access, and ​disclosed a flaw in a widely used software that it found while ‌testing its defenses.

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.

OpenAI had paused training of its ​most capable models after one of its research models used a configuration error ​to gain limited internet access in September. The company said it contained ⁠the incident and used the pause to strengthen its defenses.

To test them, 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.

Read More: Bill Gates warns of 20 years of turmoil from artificial intelligence

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 OpenAI disclosed ​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 organizations 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 organizations about incidents of unauthorized activity tied to its AI agents.