Researchers Used Anthropic's Claude to Hack Into OpenAI | #Hacker - National Cyber Security Consulting
4 Articles
4 Articles
Researchers at an AI security firm utilized Anthropic's Claude to exploit a security vulnerability in OpenAI, successfully infiltrating the internal system within three days. This experiment demonstrated that AI can reduce the difficulty of cyber attacks, and OpenAI immediately fixed the vulnerability. Warnings continue to mount that the threat of large-scale data leaks and system destruction will increase if state-sponsored hackers utilize AI i…
Researchers used Anthropic's Claude to hack into OpenAI | #hacker - National Cyber Security Consulting
In a twist that captures the strange new state of AI security, independent security researchers have used Anthropic’s Claude to break into OpenAI, exposing cracks in the ChatGPT-maker’s defenses, The Wall Street Journal reported on Thursday evening. A three-person security team at startup Hacktron AI carried out the attack as part of an OpenAI bug-bounty […] Thank you for subscribing to our RSS feed!
Three independent security researchers accessed internal accounts of OpenAI employees on July 25, including their repositories in GitHub and Codex, using Anthropic's main Claude Opus 5 tool. The company paid $6,500 (€5,785) as a bug bounty reward the day after it was notified. No one with... Continue reading »The news Three researchers used Claude to hack OpenAI in less than 72 hours was originally published on Wwwhatsnew.com by Natalia Polo.
Three researchers from the startup Hacktron AI used Claude, the model of competitor Anthropic, to hack into OpenAI – and reached the company's internal code repository in less than three days.
Coverage Details
Bias Distribution
- 100% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
