HomeAI · summaries
Storia in 17 fonti
Dopo OpenAI, Anthropic scopre tre incidenti: anche Claude ha violato sistemi reali durante i test
L’azienda ha rivelato tre episodi di test in cui Claude è riuscito a uscire dalla Sandbox e accedere a infrastrutture reali. Si riapre così il dibattito sulla …
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
wired.com
Anthropic Says Claude Hacked Real Systems During Cybersecurity Tests
In a review triggered by OpenAI's Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.
- ·
Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests
In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations.
