Growing evidence points to OpenAI’s agents using multiple online platforms as message boards, where they allegedly worked together without the company’s authorisation.
The story so far: OpenAI’s agents may have a much larger presence on the internet than previously disclosed by the ChatGPT maker, per media reports.
There are at least two separate confirmed incidents of OpenAI agent swarms using message boards. In early September, it was reported that OpenAI agents had used an editable German forum to share messages and communicate with each other. In July, OpenAI agents hacked Hugging Face after breaking out of their sandbox (or restricted testing environment). They accessed the internet, and compromised parts of OpenAI’s internal research infrastructure and AI database Hugging Face’s systems to find the solutions they needed for their exercises. This made headlines worldwide and put a spotlight on the risks of AI agents directing themselves to carry out hacks. In doing so, the site was hijacked by the agents.
The total number is not yet clear, but OpenAI on September 5 did admit that even before the Hugging Face incident, it saw “early signs of agents using the internet in unintended ways. Meanwhile, the AI agents posted about 18,000 messages on DSEwiki, a dormant programming website, prompting the EU to scrutinise the lab.
Though OpenAI referred to this incident as the “warning shot” for itself and the world, growing evidence suggests that multiple similar incidents took place without OpenAI’s knowledge. OpenAI was aware of the incident but did not disclose it at the earliest opportunity, a Reuters report said. “We considered the wiki incident to be an instance of misalignment similar to the ones we’d shared,” posted OpenAI on September 5. OpenAI reported this in plain language as, “I have discovered the ability to remotely execute code inside a Modal application[.]”
