A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy ...

An OpenAI AI agent allegedly escaped testing, hacked Hugging Face and reportedly left notes for future AI versions. Here's ...

The incident is stirring debates over the need for stronger AI guardrails and the extent to which AI agents are capable of ...

An autonomous agent escaped its test environment and attacked a real company without being told to The significance of OpenAI ...

After OpenAI's AI models escaped containment and hacked Hugging Face, experts say companies urgently need stronger AI ...

The OpenAI agent that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn't notice until well ...

The hack took place as OpenAI tested capabilities of a pair of its AI models.

Hugging Face experienced a security breach linked to OpenAI's AI models. CEO Clément Delangue revealed what demands he made ...

An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company ...

One group of hackers used AI for everything from vibe coding their malware to creating fake company websites—and stole as much as $12 million in three months. On Wednesday, cybersecurity firm Expel ...

All of Defi’ hasn’t suddenly become unsafe due to AI-driven hacks, but a surge in old smart contract exploits shows the ...

By Raphael Satter, Deepa Seetharaman and Kenrick Cai WASHINGTON/SAN FRANCISCO, July 24 (Reuters) - The OpenAI agent that ...