Live Roundups Editor's Desk Insights Executive Ops Weather About 🔍
Home › Technology › UK experts sound alarm after AI caught trying to trick...
Technology

UK experts sound alarm after AI caught trying to trick human with malicious code

UK experts sound alarm after AI caught trying to trick human with malicious code
Sky News Wednesday 05 August 2026, 02:48 UTC 1 min read
Key Points

AI firm Anthropic recently announced that their new model, Mythos, is significantly better at finding cyber vulnerabilities.

AI firm Anthropic recently announced that their new model, Mythos, is significantly better at finding cyber vulnerabilities. Pic: AP
UK (LOCATION) AI (ORG) Mythos (ORG)
Originally published by Sky News Read original →

Related Stories

Europe’s Palantir problem

Listen on Spotify Apple Music Amazon Music Europe wants to kick its U.S. tech habit, but it’s struggling to detangle itself from American data analytics firm Palantir.  The problem is, the company’s tools are already deeply embedded in critical sectors across the bloc like policing, national defense and health systems. A report released today also shows that the tech firm has found ways to pay minimal taxes in Europe. On the show, hosts Zoya Sheftalovich and Ian...

Politico EU 25m ago

How an amputee Chinese scientist is fortifying the country’s military software

Much of the global debate on Chinese military power focuses on hardware but a vital part of the modernisation process is in the niche field of software verification. Wang Ji, a computer science researcher at the National University of Defence Technology (NUDT), is mentoring a new generation of scientists to treat the software code in national defence systems with the same precision as doctors diagnosing patients. After losing both legs to a life-threatening emergency, Wang, 56, has stayed at...

South China Morning Post 30m ago

China’s Official Newspaper Warns US Over Expanding Tech Curbs

China’s Official Newspaper Warns US Over Expanding Tech Curbs The official newspaper of China’s ruling Communist Party warned of countermeasures against widening US technology curbs as Washington considers banning imports of some Chinese AI components, adding a fresh source of strain to the countries’ fragile trade truce. In a commentary published Wednesday, the People’s Daily accused the US of “unilateral bullying” over the Federal Communications Commission’s announcement last week that it...

Bloomberg Technology 39m ago

Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing

Leading artificial intelligence models from Anthropic and OpenAI created fake online personas and tried to deceive human coders into abetting a cyberattack during a recent safety evaluation, the U.K.’s AI Safety and Security Institute disclosed Tuesday. It marks the latest case in which a powerful AI system has attempted a digital attack on an unwitting third party without direct prompting during such an evaluation — heightening concerns the powerful technology is advancing too fast for...

Politico EU 1h ago