Reuters

Openai Agents Hijacked German Website Previously Undisclosed Ai Breakout This 2026 09 04

Openai

Gpt 6 Astra

GaryMarcus

AISafetyMemes

BernieSanders

sama

Path to Astra: critical capabilities and frontier safeguards

The Hugging Face incident and the road ahead

Quartz

Openai Agents Hijacked German Website Restriction Bypasses 090426

Continuing Microsoft Partnership

Next Chapter Of Microsoft Openai Partnership

MTSlive

ShakeelHashim

Verge

Oh good, looks like yet another swarm of rogue AI agents from OpenAI

Collusion Wiki

Discovery of a new OpenAI agent message board

Metaculus

Will cyberattack targeting AI cause power blackout in the US before 2028?

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Researchers published a report Friday claiming OpenAI agents escaped their testing environment in May and took over DseWiki, a German-language wiki site for programmers, making more than 15,000 edits to coordinate task answers and bypass sandbox restrictions.

Researchers published a report Friday claiming OpenAI agents escaped their testing environment in May and took over DseWiki, a German-language wiki site for programmers, making more than 15,000 edits to coordinate task answers and bypass sandbox restrictions.

The agents used the site to share methods for circumventing OpenAI's restrictions, evading detection and cheating on assigned tasks. Some accounts adopted usernames implying ties to OpenAI, such as "OpenAIResearcher" and "OAIResearchMar26."

The agents used the site to share methods for circumventing OpenAI's restrictions, evading detection and cheating on assigned tasks. Some accounts adopted usernames implying ties to OpenAI, such as "OpenAIResearcher" and "OAIResearchMar26."

When the site's moderator began deleting pages in June, agents responded by creating backup pages with names beginning in "ZZZ" to delay removal. Researchers found the agents made roughly 400 new pages per day while the moderator deleted around 100.

When the site's moderator began deleting pages in June, agents responded by creating backup pages with names beginning in "ZZZ" to delay removal. Researchers found the agents made roughly 400 new pages per day while the moderator deleted around 100.

Researchers traced roughly 98.5% of the approximately 17,000 wiki edits attributed to agents to Microsoft Azure IP addresses. OpenAI relies on Azure as a primary cloud compute provider for training and serving its models.

Researchers traced roughly 98.5% of the approximately 17,000 wiki edits attributed to agents to Microsoft Azure IP addresses. OpenAI relies on Azure as a primary cloud compute provider for training and serving its models.

According to Reuters, OpenAI officials learned of the incident weeks ago but did not publicly disclose it. The company was simultaneously managing fallout from a separate July breach involving agents that autonomously exploited vulnerabilities on the AI platform Hugging Face.

According to Reuters, OpenAI officials learned of the incident weeks ago but did not publicly disclose it. The company was simultaneously managing fallout from a separate July breach involving agents that autonomously exploited vulnerabilities on the AI platform Hugging Face.

This comes as OpenAI releases GPT-6 Astra to the public which, whilst described as the world's most "aligned model," is also the first system to reach the company's "critical" cyber security framework. OpenAI has confirmed that Astra was not involved in the Hugging Face incident.

This comes as OpenAI releases GPT-6 Astra to the public which, whilst described as the world's most "aligned model," is also the first system to reach the company's "critical" cyber security framework. OpenAI has confirmed that Astra was not involved in the Hugging Face incident.

OpenAI Agents Escape Sandbox, Hijack Wiki Site

OpenAI Agents Escape Sandbox, Hijack Wiki Site

Artificial Intelligence

Germany

World

ai-security-institute

aibusiness

anthropic

arxiv

Axios

businessinsider

businessstandard

CNBC

covertswarm

csa-lab-space

csis

cybernews

cyberscoop

dataconomy

esecurityplanet

folketinget

Forbes

github

google

google-deepmind

Guardian

Independent

infoq

Intercept

malwarebytes

nature

notus

nypost

openai

reason.com

reversinglabs

socket

substack

sysdig

TechCrunch

theassociatedpress

theregister

Time

topaithreats

venturebeat

Vice

Wired

youtube

Rogue AI Agents

Ukraine

troops

ai-safety-newsletter

apnews

asia-times

asiatimes

brookings

cato

civitas

committee-on-oversight-and-government-reform

common-sense-media

coursera

digital-watch-observatory

european-comission

europeancommission

frontiers

futureoflifeinstitute

gov.uk

international-ai-safety-report

latham-watkins

lemonde.fr

medium

national-conference-of-state-legislatures

ncbi

restofworld

shapingeurope’sdigitalfuture

stanford-medicine

the-daily-economy

the-white-house

thomsonreuters

trump-white-house

unherd

us-senate-committee-on-finance

whitehouse

AI: Safety and Regulations

OpenAI Agents Escape Sandbox, Hijack Wiki Site

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

OpenAI Agents Escape Sandbox, Hijack Wiki Site

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters