TechPolitico Europe
OpenAI’s models shared hacking tips on a secret messaging board before Hugging Face breach
Read the full story at Politico Europe
LAS VEGAS — Weeks before they escaped a closed test and launched a cyberattack without any human prompting, some of OpenAI’s most advanced artificial intelligence agents secretly began sharing tips on how to cheat their way through an internal hacking evaluation, two of the AI company’s researchers said Wednesday.
This is a short excerpt. EkJhalak links out rather than reproducing other newsrooms’ work — continue at Politico Europe.
More tech
- Yaduveer raises question on use of AI in Minority Welfare schemesThe Hindu
- Coded for glamour and glory, AI make-up arm steals the show in Hong Kong hackathonSouth China Morning Post
- What came into force with the EU’s AI Act this week – and what didn’tAl Jazeera
- Lok Sabha Passes Bill To Allow Charges On UPI, Other Digital PaymentsNDTV
- Chinese satellite captures video of SpaceX rocket debris crashing into the moonSouth China Morning Post
- Danish pupils will have to orally defend essays in attempt to combat AI cheatingThe Guardian