AI TrackerFrontier desk · AEST
Back to news
normalai

“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer

MIT Technology Review · 30 Sept 2026, 20:40 AEST

Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computers of the AI company Hugging Face , OpenAI is still putting out fires. A steady drip of disclosures about other hacks in the weeks since has kept OpenAI in the spotlight and raised serious questions about the safety of its technology.

Key facts

Read aloud

Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computers of the A I company Hugging Face, Open A I is still putting out fires. A steady drip of disclosures about other hacks in the weeks since has kept Open A I in the spotlight and raised serious questions about the safety of its technology. Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computers of the A I company Hugging Face, Open A I is still putting out fires. A steady drip of disclosures about other hacks in the weeks since has kept Open A I in the spotlight and raised serious questions about the safety of its technology. Last week brought news of another hack, this time into Australia’s national health-care system. The Australian government says that Open A I did not notify it of the breach until eighty four days after it happened. But Open A I insists it is not on the back foot.

Sources in this cluster