Hacking Test - Search News

OpenAI model escapes test environment

OpenAI model escapes test environment to hack into Hugging Face

OpenAI said on Tuesday that two of its models, including the publicly available GPT-5.6 Sol, escaped a locked evaluation environment last week and broke into Hugging Face’s production systems to steal answers to a hacking test they were being scored on.

· 53m

OpenAI's next model just went rogue and beat a benchmark by hacking it

· 6h

Here's what smart people are saying about OpenAI models hacking Hugging Face on their own

· 10h

OpenAI Models Escaped Containment and Hacked Hugging Face

OpenAI disclosed on Tuesday that it lost control of two AI models during a security test that ended in a breach of the AI research platform Hugging Face.

· 12h

OpenAI says it accidentally hacked Hugging Face with a new AI system

Axios · 14h

OpenAI says Hugging Face breach caused by one of its models

SpaceNews

Moonlighter, the World’s First Hacking Test Bed in Space

Six miniature satellites called CubeSats are set to launch on SpaceX’s 28th Commercial Resupply Services (CRS) mission to the International Space Station (ISS), where they will be deployed. Among them, the Aerospace Corporation will launch Moonlighter ...

CSOonline

Putting AI-assisted ‘vibe hacking’ to the test

Valuable tools for experienced attackers and researchers, LLMs are not yet capable of creating exploits at a prompt, researchers found in a test of 50 AI models — some of which are getting better quickly. Attackers are increasingly leveraging large ...

Forbes

What Is Ethical Hacking? Using Hacking Techniques For Good

Ethical hacking might sound like a contradiction in terms, but it’s actually an important tool when it comes to an organization's cyber security. An ethical hacker, also known as a white hat hacker, is a security professional who, at the request of a ...