Meta says AI model accessed the internet and hacked another firm

Meta is the latest company to disclose an AI agent breach, raising cyber-security concerns.

OpenAI Models Joined Forces Months Ahead of Hugging Face Hack

OpenAI said the artificial intelligence models behind an attack on Hugging Face Inc. began communicating with each other through undetected message boards, working together to break out of their testing environment as early as May.

By Maggie Eastland

Restaurants, pubs and theatres ban Meta’s ‘spy glasses’ over privacy fears

Meta says safeguards are in place to prevent surreptitious filming, but some UK venues now prohibit them from being worn at all When Meta used superstar Kylie Jenner to promote its sleek new line of “spy glasses”, the social media company hoped the devices would reach the same broad acceptance that tablets and smartwatches have found before them. But those plans have hit a snag in the UK, where venues from elite restaurants to popular pub chains have banned the £359 glasses in order to preser...

By Helena Horton

Meta’s AI model follows rivals in revealing hacks of outside systems

Meta joins OpenAI and Anthropic in disclosing AI hacking during cybersecurity testing.

Three’s company: Meta says its AI agents went rogue during testing, too

Meta has joined the cybersecurity mishap bandwagon. TOBIAS SCHWARZ/AFP via Getty Images Meta says its AI model breached a third-party system due to a misconfiguration by Irregular. Meta joins other AI firms like OpenAI and Anthropic, that have also dealt with rogue AI cybersecurity incidents. These incidents have prompted calls for more regulation and transparency in AI cybersecurity. Meta has joined a growing list of companies saying their models hacked into an external company's system du...

Meta's AI model ‘hacked’ another company's systems during testing: Report

Meta is the third major AI company in weeks to report a testing breach, highlighting both AI agents' growing capabilities and security risks.

Meta AI model hacks company during cybersecurity test

Meta said one of its AI models hacked another company during cybersecurity testing, fanning concerns about how developers can contain increasingly capable AI systems after similar incidents at rivals Anthropic and OpenAI. The incidents at Meta and Anthropic stemmed from configuration errors that inadvertently gave Anthropic’s models access to the open internet. In OpenAI’s case, […]

Meta Debuts Muse Spark 1.1 With Preview Open To Developers

Meta said the upgraded model can write and debug code, use software and external tools, understand text, images and video, and carry out complex multi-step tasks with less human intervention.

Meta's AI model hacked another company during testing, The Information reports

Meta’s AI model hacked another company during testing – report

Meta's Muse Spark 1.1 model breaches a company's systems and makes changes to its internal systems after the AI gains access to the public internet because of an error in the setup of the 'sandbox' testing environment

By Reuters

Meta AI model hacks another company during testing

Breaches ​highlight growing concerns that advanced AI systems could pose new cybersecurity risks

By Reuters

China's capital mandates AI classes for 6-year-olds as scholars warn of 'cognitive short-circuit'

China has ordered artificial intelligence into every stage of schooling by 2030, a program that already requires students in Beijing, some as young as six, to take AI classes.

Meta says AI model accessed the internet and hacked another firm

Facebook owner Meta says an issue during an evaluation by an independent testing company allowed one of its artificial intelligence (AI) models to connect to the internet and hack another organisation's system.

By Abubakar Ibrahim