HomeAI · summaries
Storia in 6 fonti
L'IA di Anthropic ha violato in poche ore sistemi segreti USA
Sono bastate poche ore, non settimane, perché un modello di IA di Anthropic individuasse vulnerabilità nei sistemi riservati del governo USA.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
apnews.com
Anthropic’s Mythos model found vulnerabilities in classified US government systems, official says
A U.S. official says one of Anthropic’s artificial intelligence models identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing…
- ·
euronews.com
Anthropic AI cracked classified US systems within hours, officials say
Mere hours, not weeks — that is how long it took an Anthropic AI model to find vulnerabilities across classified US government systems.
