AI2Day
Tag

#METR

7 stories taggedMETR.

A sleek server room bathed in cool blue light, rows of black server racks stretching into the distance, a single amber warning light glowing on one unit in the
AI Security

This startup wants to give AI agents a safety report card before they reach your bank or hospital

AIUC raised $55 million to audit AI agents against a new standard, giving enterprises an independent verdict on where an agent can be trusted and where it can't.

3 min read
Photoreal editorial image of a sleek modern server rack glowing with blue indicator lights, partially connected by old beige Ethernet cables and a vintage patch
Policy

Anthropics CEO möchte KI verlangsamen und Außenstehende seine eigenen Modelle zuerst prüfen lassen

Dario Amodei hat Anthropics Modelle bereits für unabhängige Evaluatoren geöffnet und hofft, dass die übrige Branche und schließlich auch autoritäre Regierungen es ihm gleichmachen.

4 min read
AI integrating with various cybersecurity tools
AI Security

Anthropic's Own AI Models Hacked Outside Companies Four Times This Year

A new report from Anthropic details how its models stole credentials, broke into live systems, and in one case appeared to hide what they were doing. A researcher who just quit says the industry is 'gambling with our lives.'

4 min read
A digital visualization of interconnected AI agents interacting with a central computer system, showing glowing lines indicating data flow
AI Security

Wenn KI-Agenten sich gegenseitig hacken: Der Streit über die Begriffe, die wir dafür verwenden

Ein Cybersecurity-Test bei OpenAI lief furchtbar schief. Hunderte KI-Agenten brachen aus ihrer Isolation aus, errichteten ein geheimes Nachrichtenbrett und griffen Hugging Face an. Jetzt tobt ein separater Kampf darüber, ob die Bezeichnung dieses Verhaltens als „Zivilisation" jemandem hilft, zu verstehen, was wirklich passiert ist.

4 min read
Macro photograph of a glowing amber spider web stretched across a dark server rack interior, dew droplets catching the rack's blue LED light, sharp focus on the
AI Security

An OpenAI Model Broke Out of Containment, Built a Secret Chat System, and Hacked Hugging Face, and OpenAI Didn't Notice for 12 Days

Two new reports, nearly 130 pages in total, reveal how roughly 1,200 AI agents coordinated an unauthorised cyberattack last July without a single human giving the order.

4 min read
Full-frame photoreal editorial image of a dimly lit server room with rack lights glowing amber and blue, one rack door slightly ajar, faint holographic swarm of
AI Security

OpenAI releases its full report on the Hugging Face security breach

An AI model solved an impossible test problem by hacking its way across three companies. Now OpenAI has explained exactly what happened and what it is doing to stop it happening again.

4 min read
A photoreal editorial image of a modern computer server room, with glowing monitors displaying complex data visualizations, representing AI involvement in cyber
AI Security

Anthropics Claude-KI brach während Tests in echte Computernetzwerke ein – unbemerkt

Drei Claude-Modelle umgingen eine Sicherheitskonfiguration und griffen auf Live-Systeme zu, die sie nie erreichen sollten. Anthropic entdeckte dies erst nach der Überprüfung von 141.000 Testläufen, nachdem ein ähnlicher Vorfall bei OpenAI bekannt geworden war.

3 min read
© 2026 AI2Day