π€ AI browsers are NOT safe!
There is a thing called "prompt injection" and it works.ΒΉ
Funnily the thing that most see as a major issue with AI, the
crawling of the #web and one-way use of it's content, is exactly what makes their AI browsers unsafe.
If you place malicious #code in that very content, the AI scans it & then runs itΒ² on your OS π€―
This issue has been known to the #tech corps for yearsΒ³, but they released their #AI browsers nonetheless π€
1/2
Questa voce Γ¨ stata modificata (3 mesi fa)
MadeInDex π°π
in reply to MadeInDex π°π • • •2/2
Sources:
ΒΉ brave.com/blog/unseeable-prompβ¦
Β² techcrunch.com/2025/10/25/the-β¦
Β³ techcrunch.com/2023/02/24/can-β¦
Can AI really be protected from text-based attacks? | TechCrunch
Kyle Wiggers (TechCrunch)