Hackers expose deep cybersecurity vulnerabilities in AI | BBC News
As is the case with most other software, artificial intelligence (AI) is vulnerable to hacking. A hacker, who is part of an international effort to draw attention to the shortcomings of the biggest tech companies, is stress-testing, or “jailbreaking,” the language models at Microsoft, ChatGPT and Google, according to a recent report from the Financial Times.
Courtesy of BBC News on YouTube. Watch on YouTube ↗
Sponsored
More Technology Documentaries
Cicada 3301: An Internet Mystery2018•18m•HD•★8.9
The Internet's Own Boy: The Story of Aaron Swartz2014•1h 45m•HD•★8.7
How Big Oil Conquered the World2017•1h 11m•HD•★8.6
Tesla: Master of Lightning2016•1h 26m•HD•★8.6
The Canary Islands paradox - Desalination plants: Curse or blessing? | DW Documentary2026•42m•HD•★7.7
COIN - 2022 - Brian Armstrong: A Founder's Story - Coinbase CEO2023•1h 29m•HD•★7.7
The Insane Engineering of the SR-71 Blackbird2020•19m•HD•★7.7
AI Will Save Us or Kill Us: Us & Them2024•28m•4K•★8.3
How Biotechnology Is Changing the World2021•41m•HD•★8.0
The Age of Robots: What Happens When Machines Think for Themselves2024•52m•HD•★7.9
World's Mightiest Cargo Planes: Transport Wonders of the Skies | FD Engineering2025•2h 16m•HD•★7.9
Shenzhen: China’s Most Futuristic City2026•28m•HD•★7.8