analiza aiqbench
This incident demonstrates how advanced AI models like Claude can be weaponized as automated agents to identify and exploit complex supply chain vulnerabilities in major tech infrastructure. The successful chaining of flaws via third-party software highlights that AI security risks now extend beyond model alignment to include the systemic fragility of the tools used to audit them.
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.
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 program. Hacktron reported its findings to OpenAI, which gave the startup a $6,500 award. The team managed to chain together two critical vulnerabilities to gain access…
Extras afișat conform termenilor RSS ai publicației · 81 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · 3 aug. 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · 13 oct. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
What We're Up Against: An AI Safety Crash Course
LessWrong · 24 sept. 2026