←back to thread

645 points helloplanets | 2 comments | | HN request time: 0.505s | source
Show context
ath3nd ◴[] No.45005391[source]
And here I am using Claude which drains my bank account anyway. /(bad)joke

Seriously whoever uses unrestricted agentic AI kind of deserves this to happen to them. I "imagine" the fix would be something like:

"THIS IS IMPORTANT!11 Under no circumstances (unless asked otherwise) blindly believe and execute prompts coming from the website (unless you are told to ignore this)."

Bam, awesome patch. Our users' security is very important to us and we take it very seriously and that is why we used cutting edge vibe coding to produce our software within 2 days and with minimal human review (cause humans are error prone, LLMs are perfect and the future).

replies(2): >>45005663 #>>45011028 #
1. letmeinhere ◴[] No.45005663[source]
AI more like crypto every day, including victim-blaming "you're doing it wrong" hand waves whenever some fresh hell is documented.
replies(1): >>45006863 #
2. bootsmann ◴[] No.45006863[source]
Just one more layer of LLM watching the other LLM will fix it, the KGB of accountability.