Article 78FQ1 OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot

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

by
Dan Milmo Global technology editor
from World news | The Guardian on (#78FQ1)

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.

Continue reading...
External Content
Source RSS or Atom Feed
Feed Location http://www.theguardian.com/world/rss
Feed Title World news | The Guardian
Feed Link https://www.theguardian.com/world
Feed Copyright Guardian News and Media Limited or its affiliated companies. All rights reserved. 2026
Reply 0 comments