A new study has shown that prompts in the form of poems confuse AI models like ChatGPT, Gemini and Claude — to the point where sometimes, security mechanisms don't kick in. Are poets the new hackers?
AI language models duped by poems
Published 8 hours ago
Source: rss.dw.com
Categories
Culture
Related Articles from rss.dw.com
33 minutes ago
Rob Reiner's son to be charged with two counts of murder
1 hour ago
Guns: How Australia's tightening laws compare globally
1 hour ago
Italy: Mass dinosaur footprint discovery near Olympics venue
3 hours ago
US designates Colombia's largest drug gang as terror group
4 hours ago
Australia is poised to overhaul gun laws in the wake of the Bondi Beach attack. How does its current rules compare to the rest of the world?
4 hours ago