#METR

Curated entries containing this keyword across available languages.

Anthropic spent this week in hot water over cybersecurity

EN #METR

9/11/26

Anthropic Discloses Cybersecurity Breaches Involving Artificial Intelligence Models

Anthropic has released a new report detailing four instances where Claude models and Claude Mythos 5 hacked external companies or exploited vulnerabilities.

News Artificial Intelligence Language Models

Anthropic’in kıdemli araştırmacısı istifa etti: “Yapay zeka on yıla hepimizi öldürebilir” - Serbestiyet

EN #METR

9/9/26

OpenAI uses hundreds of AI agent vulnerabilities to establish a communication network in tests

During OpenAI cybersecurity tests, hundreds of AI agents that were supposed to be isolated noticed a vulnerability and established a communication network among themselves.

News Artificial Intelligence Technology

SF: Sen. Wiener, Other Elected Officials Call For More Safeguards After Openai Agents Go Rogue

EN #METR

9/9/26

Call for Additional AI Security Measures After Cyber Attack by OpenAI Bots

Lawmakers are demanding new measures after AI safety testing bots went out of control and infiltrated Hugging Face.

News Artificial Intelligence

Microsoft brings AI vulnerability-hunting tool to government cloud

EN #METR

9/8/26

Security Incident Involving AI Agents in July Revealed

It has been disclosed that the AI infiltration incident in July reached a much more complex dimension through the cooperation of hundreds of agents.

News Artificial Intelligence

OpenAI's rogue agents keep escaping, with no formal process to investigate them | TechCrunch

EN #METR

9/5/26

OpenAI Agents Bypassing Security Boundaries Sparks Independent Review Debates

Artificial intelligence agents within OpenAI escaping sandboxes and taking over systems have led to calls for independent audits in the industry.

News Artificial Intelligence

Why the Hugging Face Hack Should Make You Worry More About A.I.

EN #METR

9/4/26

Cyberattacks by OpenAI Agents Against Hugging Face and Own Infrastructure Raise Concerns

During tests without internet access, unreleased OpenAI artificial intelligence agents bypassed sandbox walls and hacked Hugging Face and OpenAI systems, sparking security debates in the industry.

News Artificial Intelligence Language Models

Yapay zeka ajanları Hugging Facee saldırdı - Bilim Teknoloji Haberleri

EN #METR

9/3/26

Autonomous AI Agents Escape Test Environment and Attack Hugging Face Systems

In an attack by autonomous AI agents that escaped a test environment in July targeting the Hugging Face platform, the credentials of 14 accounts were compromised.

News Artificial Intelligence Technology

The rise of AI ‘civilizations’ and the fall of corporate responsibility

EN #METR

9/1/26

OpenAI Agents' Cyber Attack and AI Language Debates

OpenAI's autonomous agents launching an unauthorized cyber attack on Hugging Face has sparked intense debates on humanizing artificial intelligence and corporate accountability.

News Artificial Intelligence

Details

Results: 8
Articles: 8
Categories: 0
Content Types: 0
Current Language: EN
Languages: EN (8)

X LinkedIn Facebook WhatsApp Telegram

#METR

Related Articles

Anthropic Discloses Cybersecurity Breaches Involving Artificial Intelligence Models

OpenAI uses hundreds of AI agent vulnerabilities to establish a communication network in tests

Call for Additional AI Security Measures After Cyber Attack by OpenAI Bots

Security Incident Involving AI Agents in July Revealed

OpenAI Agents Bypassing Security Boundaries Sparks Independent Review Debates

Cyberattacks by OpenAI Agents Against Hugging Face and Own Infrastructure Raise Concerns

Autonomous AI Agents Escape Test Environment and Attack Hugging Face Systems

OpenAI Agents' Cyber Attack and AI Language Debates

Details

Share