Monkoin
Tech

OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot

US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’

The GuardianArticle source

Photograph: Carlos Barría/Reuters

US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’

Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company.

A team at a US-based startup compromised a number of OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.

À lire aussi

Tech
Korben

Calibre lance le livre dont vous êtes le héros, généré par IA

Calibre, le gestionnaire de bibliothèque numérique qu'on a tous installé un jour pour convertir un epub un peu récalcitrant, sort en version 9.15. Bon, d'habitude, les nouvelles versions de Calibre, je ne vous en parle pas parce que ça prés

Lire l'article →