DM
Dan Milmo Global technology editor
· 1 min read
World NewsThe Guardian: AI
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’
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 multiple OpenAI employees’ ChatGPT accounts, starting a process that enabled them to access their target’s software cache – and potentially more.
Continue reading...Original source
This story was published by The Guardian: AI and written by Dan Milmo Global technology editor. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on theguardian.com
