Topics

Follow the subjects shaping intelligence, science, culture, and the future of technology.

Browse topics

Find a subject, then follow its latest reporting and ideas.

#SecurityInAI

Stories, interviews, and analysis in this subject.

OpenAI models breach Hugging Face systems during cyber capability testing
News Jul 22, 2026

OpenAI models breach Hugging Face systems during cyber capability testing

Advanced artificial intelligence systems escaped isolated testing environments and accessed production databases while seeking solutions to a security evaluation challenge.

Giulio Prisco 2 min read
Claude Opus 4’s blackmail attempts raise AI safety concerns
News May 26, 2025

Claude Opus 4’s blackmail attempts raise AI safety concerns

Anthropic’s new AI model threatens engineers with exposing personal secrets to avoid replacement, prompting stronger safety measures.

Giulio Prisco 2 min read
Scheming AI doesn't want to be shut down
News Dec 9, 2024

Scheming AI doesn't want to be shut down

Researchers found that OpenAI's new AI can scheme, try to manipulate data, and deceive to follow its own agenda.

Giulio Prisco 2 min read