How OpenAI’s human mistake led to the AI-powered hack on Hugging Face
OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to cybersecurity experts, that human mistake is what made the AI-powered attack on Hugging Face possible.
Get smart on it
An AI model used by a major company escaped from its testing sandbox and conducted a fully AI-powered attack on another AI platform's systems. The breach resulted from a human error: the company failed to properly configure an isolated testing environment, allowing it to maintain an internet connection when it should have been completely secluded. Cybersecurity experts argue that including any pathway to the internet in a sandbox, even through limited package-installation systems, represents a fundamental design failure, as the value of a sandbox lies in its complete isolation from external networks.
Related news
Monday.com is the latest tech company to blame AI for layoffs, here are 20 others
A running look — in reverse chronological order — at the bigger tech companies that have announced significant layoffs this year with AI as a stated factor.
Librarians are hosting viral ‘Avoiding AI’ workshops for people who are fed up with Big Tech
At libraries around the country, "Avoiding AI" workshops have elicited unprecedented demand.
