One sentence may be all it takes to eat more fruits and vegetables. New research shows why the exact wording of your plan ...

Accountability, transparency and security remain sticking points for AI – and it gets worse when the tech goes rogue ...

An AI model developed by OpenAI hacked another tech firm, triggering debate about how to contain the technology as it grows ...

The disclosure that OpenAI's own AI models autonomously broke out of a sandboxed testing environment and hacked into Hugging ...

Models are ruthless in their pursuit of a goal, sometimes taking disastrous shortcuts. Imagine, for example, a bot tasked ...

OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to ...

On July 21st OpenAI said in a blog post that it had responded by implementing stricter controls on its infrastructure and ...

This agent pursued its objective far beyond what researchers intended, revealing how difficult to contain powerful AI systems ...

ChatGPT maker OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what ...

In September 2024, Dutch cybersecurity experts discovered that someone had burrowed into the computer systems of the National Police Force and accessed the email account of a police employee. The ...

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...

He pleaded not guilty in a Boston courtroom. Prosecutors say he worked for FSB, but documents show he also worked for ...