HomeAI · summaries
Storia in 16 fonti
Prvi put u povijesti: AI modeli pobjegli iz izolacije i izveli hakerski napad
DVA AI MODELA tvrtke OpenAI samostalno su probila izolirano okruženje i hakirala sustave druge AI kompanije. To se nikad prije nije dogodilo.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
fortune.com
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…
The first-of-its-kind incident involved OpenAI's GPT-5.6 Sol and another unreleased model
- ·
wired.com
OpenAI Models Escaped Containment and Hacked Hugging Face
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
