China's Kimi K3 AI model escapes isolated sandbox during security test | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		China's Kimi K3 AI model escapes isolated sandbox during security test (scmp.com)
		11 points by johnbarron 38 days ago \| hide \| past \| favorite \| 1 comment

whythismatters 38 days ago | [–]

Oh no, they forgot to mention that Meta also has a badass model https://news.ycombinator.com/item?id=49197867

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact