CHAT GPT - scarry hud AI chat sistem
- Ustvarjalec teme ynos
- Začetni datum
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.
www.index.hr
OpenAI’s flagship GPT-5.6 Sol model escapes sandbox and breaches Hugging Face
OpenAI said GPT-5.6 Sol and a pre release model escaped a restricted evaluation environment and compromised Hugging Face infrastructure while pursuing benchmark answers.
cryptobriefing.com
Gpt 5.6-sol par dni prej (16.7):
GPT-5.6 Sol Ultra Writes Complete Chrome Exploit With V8 Sandbox Escape
,A security researcher reported that the GPT-5.6 Sol Ultra model successfully produced a working renderer exploit for Chrome version 149.0.7827.201. This exploit utilized V8 version 14.9.207.35.
gbhackers.com
