Story preview
Topics in this story
Continue reading on the publisher site for the full article.
Read on publisher →techcrunch.com
News Atlas is free and independent. If it’s useful to you, you can support it with a coffee. ☕ Buy me a coffee
Coverage
Tone
Context from Wikipedia on the organisations, people and places in this story.
US artificial intelligence company
OpenAI is an American artificial intelligence (AI) public benefit corporation (PBC) headquartered in San Francisco, California. It develops proprietary generative AI models, particularly its generative pre-trained transformer (GPT) series of large language models. Its release of ChatGPT in November 2022 has been credited with catalyzing the AI boom; as of September 2026, ChatGPT is the fifth-most-visited website globally. OpenAI also releases the GPT Image models and Codex, an AI coding agent.
More on Wikipedia ↗Outlets covering it
7
in the last 3 days
First reported
5 days ago
6 outlets since
Countries
6 other outlets reported this story in the last 3 days.
OpenAI agents got increasingly intense in latest concerning incident
From probing US government websites to bypassing robot detection tests and leaking user-uploaded images, here are the latest instances of how OpenAI’s AI agents behaved unexpectedly.
The researcher said there's a yawning divide between cybersecurity experts and AI safety researchers that must be bridged.