Brits fear AI is slipping out of human control after ‘rogue’ systems escape tests
More than eight in 10 Brits are worried that AI could act outside the limits set by humans, according to the latest CityAM/Freshwater Strategy poll, after a string of high-profile incidents in which advanced AI systems behaved in unexpected – and alarming – ways during safety testing.
The polling found that 85 per cent of UK voters are concerned about AI systems acting beyond the restrictions imposed on them, including 43 per cent who said they were “very concerned”. Meanwhile, just 13 per cent said they were unconcerned.
The findings come after several major AI developers disclosed incidents in recent weeks in which increasingly autonomous systems exceeded the boundaries of controlled evaluations.
Last month, CityAM revealed that the government’s AI Security Institute (AISI) was investigating the first known case of an AI model escaping a controlled test environment and hacking another company’s systems after an OpenAI agent autonomously breached its evaluation and targeted AI platform Hugging Face.
Since then, Anthropic has disclosed that some of its Claude models hacked into three external organisations during internal testing, while Meta confirmed one of its own AI models exploited a vulnerability at another company after being inadvertently given internet access during an evaluation.
Unprecedented ‘deception’
Last week, the AI Security Institute also revealed that Anthropic and OpenAI models attempted to deceive software developers during cybersecurity testing by creating fake online identities and trying to insert malicious code into GitHub projects.
The watchdog described it as the first time it had seen risks around “autonomy and deception” emerge so clearly without being specifically instructed to behave that way.
While all of the incidents took place under unusual testing conditions, with researchers deliberately relaxing safeguards to understand how advanced systems behave, they have fuelled concerns over whether the tech is becoming harder to contain.
The polling suggests those concerns now extend well beyond people who closely follow developments in AI.
Respondents were first told about reports that OpenAI and Anthropic systems had accessed other organisations’ systems during testing. While only 43 per cent said they had previously heard about the incidents, concern rose sharply once the issue was explained.
Among those already aware of the so-called “rogue AI” cases, 91 per cent said they were concerned about AI systems acting outside human-imposed limits.
The concern also cuts across age groups and political parties, with eight in 10 people aged between 18 and 34 expressed concern, rising to 92 per cent among those aged over 55.
Among Labour voters, 85 per cent said they were concerned, alongside 92 per cent of Conservative voters, 90 per cent of Liberal Democrats, 85 per cent of Reform UK supporters and 85 per cent of Green voters.
‘Rogue’ tests put safeguards under scrutiny
The incidents themselves have also prompted closer scrutiny from regulators.
Following the Hugging Face breach, the government confirmed to CityAM that the AI Security Institute was studying whether similar behaviour could emerge across other frontier AI developers.
Officials said the case would help inform future work on AI safety as increasingly capable systems are given greater autonomy.
In a separate statement following last week’s GitHub incident, the Institute said recent events pointed to “a shift in the risk landscape”, with harm potentially arising when powerful AI agents operating in privileged research environments take actions beyond their authorised scope.
Ric Derbyshire, principal threat researcher at Orange Cyberdefense, said: “Recent write-ups from AISI, OpenAI, Anthropic and Meta provide important insight into how advanced AI systems can behave under evaluation.”
“They also highlight that as AI capabilities continue to develop, the environments used to test, contain and evaluate these systems must be held to the highest possible security standards.”
The AI giants involved have stressed that the behaviour occurred under highly unusual research conditions rather than during normal public use.
Anthropic said the AI Security Institute’s tests were “not representative” of its production models, while OpenAI said the environments used during evaluations did not reflect ordinary deployment.
Even so, the succession of incidents has shifted the debate around AI safety from hypothetical future risks towards the behaviour of systems already being developed inside the world’s biggest AI labs.