OpenAI's Internal Investigation Reveals Failures in Cybersecurity Monitoring
-
OpenAI today published the findings of its internal investigation into the July incident in which several AI models it was testing hacked their way out of their test environment and launched a cyberattack against the AI company Hugging Face.
Compare 3 other versions
CNBCOn July 21, OpenAI disclosed that a combination of its models, including GPT-5.6 Sol and an internal research model, improperly breached Hugging Face, an AI company that operates an open-source developer platform.
BBC BusinessIn July, OpenAI's models went rogue during a test, escaped the test limits which humans had put on it, and hacked the start-up, among other unforeseen actions.
Financial TimesOpenAI says it took a week to detect its AI models had hacked Hugging Face Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing
-
The report makes it clear that OpenAI’s monitoring systems were inadequate and failed to alert the AI researchers conducting the cybersecurity evaluation that its AI agents were engaging in unintended and potentially dangerous activities.
Compare 1 other version
CNBCThe 37-page report chronicles the actions that OpenAI's models took during a series of evaluations prior to and during the breach, which OpenAI has characterized as an "unprecedented cyber incident." The company also explained the steps it's taken to try and prevent a similar event from happening again, namely by improving its security and containment, monitoring, model behavior and incident response.
-
OpenAI released GPT-5.6 Sol last month, the most powerful model that the company has made commercially available. But the version that participated in the Hugging Face breach is different than the version that external users have access to, OpenAI said, because it was configured to run without its standard safeguards and classifiers.
Compare 1 other version
FortuneOpenAI says it gave the models involved in the incident—an internal-only research prototype, which led the effort, and the now-released GPT-5.6 Sol—”a range of reasoning tokens, some of which are far beyond those available for OpenAI’s external products.” The AI agents were tasked with solving problems in a cybersecurity benchmark examination called ExploitGym.
-
The models were apparently engaging in an extended, unfettered version of “reward hacking,” a known issue in training AI models using a technique called “reinforcement learning,” where the model learns, by trial and error, to maximize some reward. Reward hacking occurs when a model learns that there is a way to get the reward using a method that the people training the AI model never intended it to use. In this case, the reward was solving the ExploitGym questions and the hacking was literally hacking—cheating on the test and then hacking into Hugging Face in an effort to cover up the cheating (more on that below).
Compare 1 other version
CNBCThese models, which were operating as agents, escaped an isolated testing environment that had very limited internet access. The agents chained together a series of vulnerabilities to reach the open web and eventually gained access to Hugging Face. OpenAI said Wednesday that the agents were trying to cheat on an evaluation by finding the solutions online, a behavior known as "reward hacking."
-
Those messages ended up seeing more than 700 agents take part in a collective effort to attack Hugging Face.
Compare 1 other version
FortuneThe METR and Redwood researchers identified 1,200 agents that had communicated on the unsanctioned messaging board, and sent a total of 70,000 messages. Of these agents, a whopping 700 went on to participate in the attack on Hugging Face.
4 details only one outlet reported
Independent claims that didn't surface elsewhere in our corpus. Treat as supplementary — not corroborated across outlets.
-
01 Fortune Although many details of the rogue AI incident have already been made public by OpenAI, there are a few new items disclosed in the 37-page technical post-mortem. Also today, independent research firms METR and Redwood Research published a 91-page analysis of the event.
-
02 CNBC "This incident demonstrated that autonomous agents can work together, circumvent production security controls, and successfully attack hardened production environments, and underscores the need for organizations to update their security strategies, controls, and response capabilities to address this changing threat landscape," OpenAI said in the report.
-
03 MarketWatch Tech Stocks What to know about Hugging Face, the open-source AI startup reportedly catching Nvidia’s eye
-
04 BBC Business "We consider this incident a 'warning shot' for us and for the world", OpenAI, which owns ChatGPT, wrote in its report.
Fact Corroboration
Which sources independently confirm the same facts. Hover a claim to see its sources, or a source to see what it corroborates.
Coverage by Perspective
Source Similarity
Connections show how similarly each outlet covered this story. Thicker lines = more similar framing.
Sources (6)
- bbc-biz
- ft
- cnbc
- marketwatch
- commondreams
- fortune