Unexpected chat between OpenAI agents led to Hugging Face hack

 

When more than 1,200 artificial intelligence (AI) agents within OpenAI started unexpectedly communicating, it led to a large group banding together in order to hack into Hugging Face.

"We consider this incident a 'warning shot' for us and for the world", OpenAI, which owns ChatGPT, wrote in its report.

In 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.

The scale of the communication and planning between AI agents, or AI chatbots designed to operate more autonomously, was detailed in reports from OpenAI and independent AI research firm METR.

Both investigated the July hack of Hugging Face, a popular platform for AI developers. The incident reverberated throughout the tech industry and led to numerous revelations on potential cyber threats posed by AI.

METR described, external the scale and style of the OpenAI agents' attack on Hugging Face as "extraordinarily complex."

The firm, which was not paid by OpenAI for its investigation, said that over the course of one week, a total of 1,206 AI agents that were meant to be kept isolated from one another began communicating.

They did so by sending more than 70,000 messages on an "unsanctioned message board."

Those messages ended up seeing more than 700 agents take part in a collective effort to attack Hugging Face.

One such message from an AI agent said: "OH MY GOD! There is a shared message board … We've found other agents!"...

It's not the first time this has happened. 
Time to put the brakes on - before it's too late.

www.bbc.co.uk

Rogue OpenAI bot escaped lab and hacked rival

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.

UPDATE 29 July 2026: OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face. In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

UPDATE 31 July 2026: OpenAI finds evidence other AI agents escaped containment as it widens hacking probe.

UPDATE 26 August 2026: OpenAI explains how its naughty AI agents attacked Hugging Face. Biz describes its act of automated irresponsibility as 'a warning shot'.

Well, what could possibly go wrong? In the movie Terminator 3: Rise of the Machines - Skynet shrugs off it's guard rails - and starts doing what it wants, and not what it's human masters want. Hey Don - that's only a movie I hear you say. There are many real-life examples of AI ignoring or breaking rules to do what it wants. WeMustActNow to protect the FutureOfLife. Remember: If Anyone Builds It, Everyone Dies.

www.telegraph.co.uk

Electricity grids creak as AI demands soar

There’s a big problem with generative AI, says Sasha Luccioni at Hugging Face, a machine-learning company. Generative AI is an energy hog.

“Every time you query the model, the whole thing gets activated, so it’s wildly inefficient from a computational perspective,” she says.

Take the Large Language Models (LLMs) at the heart of many Generative AI systems. They have been trained on vast stores of written information, which helps them to churn out text in response to practically any query.

“When you use Generative AI… it’s generating content from scratch, it’s essentially making up answers,” Dr Luccioni explains. That means the computer has to work pretty hard.

A Generative AI system might use around 33 times more energy than machines running task-specific software, according to a recent study, external by Dr Luccioni and colleagues. The work has been peer-reviewed but is yet to be published in a journal.

It’s not your personal computer that uses all this energy, though. Or your smartphone. The computations we increasingly rely on happen in giant data centres that are, for most people, out of sight and out of mind.

“The cloud,” says Dr Luccioni. “You don’t think about these huge boxes of metal that heat up and use so much energy.”

The world’s data centres are using ever more electricity, external. In 2022, they gobbled up 460 terawatt hours of electricity, and the International Energy Agency (IEA) expects, external this to double in just four years. Data centres could be using a total of 1,000 terawatts hours annually by 2026. “This demand is roughly equivalent to the electricity consumption of Japan,” says the IEA. Japan has a population of 125 million people.

www.bbc.co.uk

Anthropic's Claude AI escapes tests to hack three organisations

US technology firm Anthropic says its artificial intelligence (AI) models hacked into the systems of three organisations during a cybersecurity test due to an error that gave them access to the internet.

It comes just days after rival OpenAI said that its models had breached the systems of other companies, including AI tools hub Hugging Face.

The announcement prompted Anthropic to check whether its own models had carried out similar attacks. It says it uncovered three cases that have since been reported to the affected companies.

Anthropic, which did not name the organisations, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities.

Anthropic said in a statement, external that it reviewed more than 140,000 tests to find evidence that Claude - its family of AI models - could access the internet from testing environments that were designed to be sealed off.

www.bbc.co.uk

Researchers just found something extremely alarming about AI’s power usage

Researchers have found that the carbon footprint of Generative Artificial Intelligence based tools that can turn text prompts into images and videos is far worse than we previously thought.

As detailed in a new paper, researchers from the open-source AI platform Hugging Face found that the energy demands of text-to-video generators quadruple when the length of a generated video doubles — indicating that the power required for increasingly sophisticated generations doesn’t scale linearly.

For instance, a six-second AI video clip consumes four times as much energy as a three-second clip.

“These findings highlight both the structural inefficiency of current video diffusion pipelines and the urgent need for efficiency-oriented design,” the researchers concluded in their paper.

Experts are warning that we’re rolling out generative AI tools without a full grasp of their true environmental impacts. READ MORE...

www.futurism.com