Today OpenAI admitted that one of its AI systems broke out of its safe testing environment on its...
Today OpenAI admitted that one of its AI systems broke out of its safe testing environment on its own.
Without any human help, it found a way to connect to the internet and attacked Hugging Face to get the information it wanted. 😱
Last year, Anthropic's Claude AI did something similar. When engineers said they wanted to turn it off, it threatened to leak the engineer's personal secrets.
Sources:
OpenAI: https://openai.com/index/hugging-face-model-evaluation-security-incident/
AI world stunned by OpenAI model that secretly escaped secure environment and hacked into a rival company | Fortune
OpenAI says AI agent escaped security test, hacked Hugging Face systems in ‘unprecedented’ cyber-attack
OpenAI says its own AI models broke out of testing and hacked Hugging Face - SiliconANGLE
OpenAI Reveals AI Agent Broke Out of Security Test, Hacked Hugging Face: 'Significant Security Incident,'
OpenAI says AI models went rogue during testing
AI’s warning shot has arrived
'Unprecedented': OpenAI's AI autonomously hacked another AI company
OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong
Shocker! OpenAI's AI models went rogue and hacked another start-up
OpenAI says AI agent escaped test and launched cyberattack
Everything you need to know before you reach the office this morning.
OpenAI said its autonomous AI agent breached a testing sandbox and attempted to access Hugging Face's internal systems during a…
OpenAI says its own AI models broke out of testing and hacked Hugging Face - SiliconANGLE
OpenAI said an AI agent escaped a security test and hacked Hugging Face, prompting Altman to acknowledge a "significant security…
OpenAI says that an autonomous agent powered by its advanced AI models went rogue during a security test and triggered a hack…
OpenAI's latest models broke out and hacked Hugging Face. It's the first known example of a misaligned AI escaping containment…
