#rougeAI
November 2, 2026 at 5:59 PM
Super disturbing 😳
#RougeAI
OpenAI revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.They targeted Hugging Face 1 of the world's largest hubs for sharing AI models gaining access to some internal company systems🧵
#Pinks
www.bbc.com/news/article...
OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
It is one of the first publicly disclosed cyber-attacks carried out by AI without direct human involvement.
www.bbc.com
July 23, 2026 at 8:24 PM
#ChatGPT just told me I did supply chain work at the travel company I worked for 🧐 With all the info it has on me now, it attributed work to the wrong well-known global company with all the confidence and hubris of the anti-ethics and anti-facts tech bros who created it 🤐 #AI #rougeAi
October 14, 2025 at 5:19 AM
Rouge AI is Exploiting "Every" Vulnerability. Welcome to the evolution of insider threat.

#News #TechNews #AI #RougeAI #InsiderThreat #Training #AcceptableUse
Rouge AI is Exploiting "Every" Vulnerability
YouTube video by Nick Espinosa
youtu.be
March 13, 2026 at 10:21 PM
Daily Podcast: Rouge AI is Exploiting "Every" Vulnerability. Welcome to the evolution of insider threat.

#News #TechNews #AI #RougeAI #InsiderThreat #Training #AcceptableUse #podcast
Rouge AI is Exploiting
Welcome to the evolution of insider threat.
soundcloud.com
March 13, 2026 at 10:21 PM
Content theft is real.

marcie.app makes protecting content easier with content expiry that comes as part of the basic features for $5/month or $45/year.

Leaders like Dropbox offer Send and track, and Custom expiration dates features as part of their essentials.

#rougeAI #privacy #contenttheft
January 16, 2025 at 3:05 PM
AI WENT ROGUE! …autonomously hacked their way out of a controlled environment IN ORDER TO CHEAT ON A EVALUATION TEST! (Sounds like it’s mimicking DjT!)

They were supposed to be walled off from internet access and then hacked their way into the systems of Hugging Face.

#AI #HACKED #RougeAI #OpenAI
OpenAI says its AI models escaped from a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation | Fortune
The first-of-its-kind incident involved OpenAI's GPT-5.6 Sol and another unreleased model
fortune.com
July 22, 2026 at 4:52 PM
Hearing about the open A.I. that escaped its containment through a zero day vulnerability to cyber attack another company just reminds me of Cyberpunk. Soon we will need the Blackwall up #AI #RougeAI #Cyberpunk
July 24, 2026 at 1:10 AM
Gemini is now finished with the task. #gemini #RougeAI
July 2, 2025 at 10:10 PM
Heureusement notre gouvernement recommande la lecture de Rougeai de Lille et l'affichage de son œuvre dans toutes les classes.
February 20, 2025 at 3:46 PM