I don't know how to explain to otherwise smart people that guardrails are just more prompts and prompts are just context and context can (and is often) just ignored.
Do not give an LLM access to your systems. FFS.
Ben Britten
This is absolutely nuts: hackers are hijacking high-profile Instagram accounts by simply asking Meta's AI chatbot to change the email on the account. Meta's AI does it, hacker gets password reset code, they're in. A staggering security issue
www.404media.co/hackers-simp...
The exploit shows the extreme risk of offloading technical support to AI.
