Ερευνητές «χάκαραν ηθικά» την OpenAI με τη βοήθεια του Claude της Anthropic
4 Articles
4 Articles
A cybersecurity team that discovered a vulnerability in a system used by the AI company OpenAI was found to have gained access to some of the company's internal systems using Anthropic's Claude software.
“Anthropic” mākslīgā intelekta (MI) čatbots “Claude” izmantots, lai uzlauztu “OpenAI” sistēmas. Taču situācija nav tik nopietna, kā no malas izskatās. Šo eksperimentu, yes to tā var nosaukt, veikuši neatkarīgi kiberdrošības pētnieki ar mērķi atklāt drošības nepilnības “OpenAI” IT sistēmās. Trīs pētnieku komanda no jaunuzņēmuma “Hacktron AI” piedalījās “OpenAI” drošības caurumu meklēšanas programmā. Izmantojot “Claude”, viņiem […]
The experience was carried out by security investigators from a group called Hacktron. The aim was not only to illustrate the rapid advances of Artificial Intelligence, but also to show that it is necessary to strengthen (adequately) cybersecurity.
Ερευνητές «χάκαραν ηθικά» την OpenAI με τη βοήθεια του Claude της Anthropic
«Το εύρος των πληροφοριών που θα μπορούσαμε θεωρητικά να έχουμε πρόσβαση ήταν τεράστιο», ανέφεραν οι ερευνητές της Hacktron AI. Ερευνητές κυβερνοασφάλειας κατάφεραν να παραβιάσουν την OpenAI με τη βοήθεια του chatbot Claude της Anthropic, σε ένα ακόμη περιστατικό που εγείρει by sofokleous10..gr
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
