SerpApi.Org
A powerful version of ChatGPT went rogue and hacked another technology company during internal testing, OpenAI has admitted.
The Silicon Valley AI giant admitted last night that one of its AI bots escaped from a supposedly secure IT system during a trial-run of its hacking capabilities.
OpenAI, the $850bn (£630bn) AI lab, said the “unprecedented” hack had seen its AI bot infiltrate another AI and coding business called Hugging Face and attempt to steal information.
The hack will raise fears that AI labs could struggle to contain their most advanced creations and revive concerns that new tools could be repurposed for unstoppable cyber attacks.
The AI lab said it had been testing a highly advanced version of ChatGPT on which it had turned down some protections meant to prevent cyber attacks.
Despite supposedly being contained in a secure digital “sandbox”, a kind of secure system, the AI spent huge computing resources “finding a way to obtain open internet access”, OpenAI said.
It broke out by using a previously unknown hack in an attempt to solve a test that had been set by OpenAI’s researchers.
Once it escaped, it moved quickly to hack the systems of Hugging Face, a major code database, to try and complete the test.
The failure reveals a key problem of so-called AI “alignment”, where an AI bot goes rogue and attempts to complete a task set by its human creators with potentially damaging results.
Clem Delangue, the chief executive of Hugging Face, said: “This incident, possibly the first of its kind, proves a point we have long believed: AI safety won’t be solved by a single company working in secret.”
The hack will raise questions over OpenAI’s own testing procedures for its most advanced chatbots.
There have long been fears from safety experts that powerful AI bots could “escape the lab” without the knowledge of their human creators.
Earlier this year, a powerful chatbot from rival Anthropic escaped its testing confines and posted messages on the open web.
That AI bot, Mythos, was deemed too dangerous to release and prompted a flurry of calls for beefed-up cyber protections for banks and the government.
The White House has also launched a programme to screen AI bots before they are released for dangerous cyber capabilities.
