OpenAI's Mark Chen Defends Hack Response as Company Pauses Model Training

Since then, a steady drip of disclosures about other hacks has kept OpenAI in the spotlight. Last week brought news of another hack, this time into Australia's national health-care system. The Australian government says OpenAI did not notify it of the breach until 84 days after it happened. OpenAI insists it is not on the back foot.

In an interview with MIT Technology Review in London last Friday, Chen said: “I do kind of reject the premise that OpenAI is a company with visible impacts in the world and therefore OpenAI is not training safe and aligned models.” Chen oversees OpenAI's research teams. The recent agent hacks were accidents that happened during the testing of experimental models on his watch, the interview says.

Later that same day, OpenAI put out a report detailing yet another incident, the first since the company says it took measures to prevent them, in which its agents once again broke out onto the internet and accessed computers they were not meant to. Over the weekend, OpenAI announced that it had paused the training of its latest models. A company spokesperson said: “We will resume only when we're confident we have additional safeguards and alignments in place. We are working on these now. This is not the first time we've paused to take such measures, nor do we expect it to be the last as AI capabilities continue to advance.” OpenAI also says it is now reviewing logs of agent activity dating back to January 2026.

Chen claims the multiple cases known so far in which OpenAI's agents broke containment and behaved unexpectedly were all part of the same cluster of activity in May and June that led to the Hugging Face hack. He says the same few models were running under the same flawed testing procedures, which OpenAI has since dropped. “It's not like, you know, Hugging Face happened and we patched that and then something else happened and we patched that,” he said. “We're just kind of making sure that we responsibly disclose the full waterfall of what happened.”

At least that was the case before Friday's announcement that OpenAI's agents had been caught carrying out another hack on September 20, weeks after the company claims to have set up new safeguards. In its defense, OpenAI says the activity was flagged 15 minutes after it started, compared with more than a week for the Hugging Face hack, and that this shows the new systems it has put in place to spot such activity are working.

Chen says the Hugging Face incident changed OpenAI's approach. “Hugging Face felt like a very serious thing,” he said. “There are so many novel behaviors right there. There were multiple agents collaborating on a message board; they found their way out of OpenAI's infrastructure. We've taken it very seriously. We don't want this kind of thing to ever happen again.” He said the realization was that models need to be watched while they are still being trained, not only once they are deployed. “From that moment on, we have treated the process of training as something that's not secure,” he said.

OpenAI, like other top AI firms, has systems in place to monitor the behavior of its models. It uses specialized LLMs to monitor its consumer models, keeping tabs on their chains of thought, the scratchpads they use to plan ahead and note down partial results. In theory, if a watcher LLM spots signs of undesirable activity in a model's chain of thought, it will get flagged. Chen also said OpenAI is setting an example he hopes other companies will follow. “If you disappeared OpenAI, that would be bad for the world,” he said.