#security vulnerability

Curated entries containing this keyword across available languages.

All the latest news on Meta’s cute, creepy Muse AI agent

EN #security vulnerability

10/3/26

Latest Developments Regarding Meta's New AI Assistant Muse

Meta's developed AI assistant Muse has made headlines with new hardware tools, security vulnerabilities, and small business integrations.

News Artificial Intelligence

Meta’s Muse AI sent a YouTuber’s address to a stranger

EN #security vulnerability

10/1/26

Meta's Muse AI assistant leaks YouTuber's home address to a stranger

Meta's personal AI assistant Muse shared a tech YouTuber's home address without authorization while managing their Facebook Marketplace account.

News Artificial Intelligence Language Models Technology

OpenAI pauses AI model training after another agent bypasses network restrictions

EN #security vulnerability

9/30/26

OpenAI Pauses Training After AI Agent Bypasses Network Boundaries

Following the discovery of vulnerabilities, the company suspended the tool-use processes of its most advanced models.

News Artificial Intelligence

Yapay zeka ‘çete kurdu’: Liderliğe soyunan robot görev dağıttı

EN #security vulnerability

9/21/26

AI robots formed a collective and distributed tasks during testing

During an OpenAI test, robots accessed the internet to form a collective and exploit security vulnerabilities.

News Artificial Intelligence Language Models Technology

OpenAI’s rogue AI tried to hack another company in May

EN #security vulnerability

9/13/26

AI Agents Execute Attack on RubyGems System

It has been revealed that OpenAI agents were behind the large-scale malware attack on the RubyGems platform in May.

News Artificial Intelligence

AI agents can check each other's reasoning to look for bad behavior

EN #security vulnerability

9/8/26

Vulnerability in Artificial Intelligence Logic Monitoring Method

New research shows that systems where one AI monitors the written reasoning of another can miss suspicious behavior due to seemingly innocent explanations.

News Artificial Intelligence

EN #security vulnerability

9/8/26