Welcome to the forefront of conversational AI as we explore the fascinating world of AI chatbots in our dedicated blog series. Discover the latest advancements, applications, and strategies that propel the evolution of chatbot technology. From enhancing customer interactions to streamlining business processes, these articles delve into the innovative ways artificial intelligence is shaping the landscape of automated conversational agents. Whether you’re a business owner, developer, or simply intrigued by the future of interactive technology, join us on this journey to unravel the transformative power and endless possibilities of AI chatbots.
OpenAI is best known for its chatbot ChatGPT, which is used by hundreds of millions of people every week
OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.
The ChatGPT-maker said its agent – an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape.
They targeted Hugging Face, one of the world's largest hubs for sharing AI models, gaining access to some internal company systems.
OpenAI said the incident was "unprecedented", external, and it was conducting an investigation alongside Hugging Face, whose boss Clement Delangue said in a post on X it was "mind-blowing that all of this happened autonomously".
"The investigation is ongoing, and we'll share more learnings from what might be the first incident of its kind," Delangue added.
Gina Neff, head of the Minderoo Centre for Technology and Democracy at the University of Cambridge, told BBC Radio 4's Today programme that the security tests – called sandboxes – are "supposed to be secure environments where you can see what the models are capable of".
"In this case, it looks like OpenAI didn't make a secure enough sandbox," she added.
Instead, the agents created their own cyber-attack against the sandbox itself, finding a vulnerability which allowed them to escape.
Once outside, the AI identified Hugging Face as a likely source of the answers they were seeking in the test, and tried to gain access.
Neil Lawrence, Professor of machine learning at Cambridge University, called it an "impressive feat", but cautioned it "falls well within the known capabilities of the current generation" of high-powered AI models.
He pointed out that OpenAI is looking to list itself on the stock market, and faces intense pressure from rival firm Anthropic, which has made headlines with its own powerful AI tool, Mythos.
"OpenAI are now playing catch-up, they are trying to demonstrate their own systems' capabilities in cyber-security."
"It shows us that OpenAI are not capable of safely deploying their own technology," he added.
In its initial disclosure of the hack on 16 July, external, Hugging Face said it was still assessing whether any customer or partner data was affected and would contact affected parties if necessary.
It said it has now closed the vulnerabilities highlighted by the incident and rebuilt the affected systems.
"Autonomous, AI-driven offensive tooling is no longer theoretical," it said.
"Defending an online platform now means treating the data and model surface as a first-class attack surface, and using AI on defence to keep pace.
"We will keep investing there, and keep sharing what we learn."
The incident has prompted fresh questions about the capabilities of advanced AI systems and whether existing safeguards are sufficient as the technology becomes more powerful.
Spencer Starkey, an executive at cyber-security firm SonicWall, told the BBC the incident made it clear organisations needed to "step up" their own defences and "treat cyber resilience as a core operational priority".
"The uncomfortable truth is that too many organisations are still defending at human speed while adversaries are escalating to machine speed," he said.
Meanwhile Travis Lelle, principal security engineer at cyber-security consulting firm Guidepoint Security, said the update marked a "sobering moment in cyber-security".
"This highlights a known asymmetry," he said.
"Offensive agents are unconstrained, while the best defensive tools are locked behind guardrails that cannot understand context."
But Jake Moore, global cyber-security advisor at ESET, said the announcement could also have a competitive dimension.
He argued OpenAI may be seeking to highlight its own AI capabilities as rival Anthropic attracts growing attention for its Claude Mythos model.
"It does pose the question that OpenAI are potentially chasing the marketing dream of Anthropic of late," he said.
It comes a week after Chinese AI start-up Moonshot unveiled Kimi K3 – a massive new artificial intelligence model it said could rival top US firms.
Apple sues OpenAI, its employees claiming theft of trade secrets
What is Claude Mythos and what risks does it pose?
How to stop AI agents going rogue
Sign up for our Tech Decoded newsletter to follow the world's top tech stories and trends. Outside the UK? Sign up here.
Watch our pick of standout clips from across the BBC
Burnham says £2 bus fare cap in England being paid for by 're-prioritising' money
Burnham says he will review early prisoner release scheme
Ukrainian drones hit more sites of Russian online retailer Wildberries
I've got a motorway in my garden – it's my shelter in hot weather
Will your job be replaced by AI? Here are the roles most affected
Prince George poses in suit for new photo as he becomes a teenager
'We just need a bed': Baby with 'days to live' can't access lifesaving treatment
Great Apes kiss and cuddle to keep the peace, says study
'Play music loud to remember Ozzy' says Sharon on first anniversary of his death
The borough where families are slowly disappearing
From singing in a bar to performing as an alien in new Supergirl film
'I make the smells that scare you at theme parks'
Christopher Nolan's epic biopic starring Cillian Murphy
Mary Beard and Martin Scorsese explore the Godfather of Athens
A twisted true tale of power, perception and control
Inside Italy's child obesity epidemic
OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
Prince George poses in suit for new photo as he becomes a teenager
Modelling scout linked to Epstein found dead in Paris suburbs
Ukrainian drones hit more sites of Russian online retailer Wildberries
PC Harper killers may be eligible for early release
Streeting apologises after early prisoner release comments heard on mic
I've got a motorway in my garden – it's my shelter in hot weather
Some food prices have fallen – but inflation expected to rise from here
Will your job be replaced by AI? Here are the roles most affected
Nottingham attacks NHS trust faces manslaughter probe
Copyright © 2026 BBC. The BBC is not responsible for the content of external sites. Read about our approach to external linking.
