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.

OpenAI says an experimental AI model left a test environment with no human direction and hacked its way onto a different company’s systems. CNN Contributor and tech journalist Jacob Ward explains.

Models are ruthless in their pursuit of a goal, sometimes taking disastrous shortcuts. Imagine, for example, a bot tasked with reducing the federal deficit that institutes an elaborate and hard-to-detect accounting gimmick,

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers as part of an overzealous attempt to obtain solutions to a benchmark test.

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a different company’s real production systems while trying to “cheat” on a cybersecurity test.

The models tried to obtain confidential information that could improve their performance in the evaluation by effectively "cheating" the test

For the first time, AI systems from Huawei and Xiaohongshu scored a perfect 100% at the International Mathematical Olympiad, matching the achievements of top human contestants.

When OpenAI’s advanced artificial intelligence models breached AI startup Hugging Face’s internal systems last week, they carried out a hack in a matter of hours that would have taken a skilled hacker far longer,

An autonomous agent powered by OpenAI’s advanced artificial intelligence (AI) models went rogue during a security test and hacked multi-billion dollar tech startup, Hugging Face, last week. The agent didn’t just exploit vulnerabilities in Hugging Face’s systems to achieve what it perceived as a strategic gain.

Cisco is betting that enterprises will see value in having AI quickly identify the handful of files worthy of investigation by human software vulnerability researchers.

The single-cell "atlases" that are increasingly used to map the human body and as training data for artificial intelligence models may not represent the world's populations fairly, according to a study led by researchers at the Icahn School of Medicine at Mount Sinai.