Researchers Used Anthropic's Claude to Hack Into OpenAI
15 Articles
15 Articles
An American startup accessed the ChatGPT accounts of several OpenAI employees. The American company rewarded ethical hackers.
Researchers used Anthropic's Claude to hack into OpenAI
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.
Researchers have been able to access the ChatGPT accounts of OpenAI employees during a security exercise organised by the company, using an Anthropic d的IA model. ...
Artificial intelligence agents have the ability to wreak havoc on the network. This is demonstrated by security incidents involving this kind of technology over the past few months. Now, a team of security researchers from Hacktron AI has announced that it has been able to 'hack' the IA OpenAI company successfully through the use of Claude Opus 5, one of the most advanced models of Anthropic. And, to achieve this, it took only 72 hours.«I don't …
BizToc
IT Security News - cybersecurity, infosecurity newsResearchers used Anthropic’s Claude to hack into OpenAI
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…
Cybersecurity experts used Anthropic's Claude model to hijack an OpenAI employee's account and gain access to the company's code repository. This is another incident involving autonomous AI systems.
Coverage Details
Bias Distribution
- 40% of the sources are Center, 40% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
