logoalt Hacker News

dvtyesterday at 10:25 PM2 repliesview on HN

We do, and the comparison is apt. We are the ones that hydrate the context. If you give an LLM something secure, don't be surprised if something bad happens. If you give an API access to run arbitrary SQL, don't be surprised if something bad happens.


Replies

stavrosyesterday at 10:33 PM

So your solution to prevent LLM misuse is to prevent LLM misuse? That's like saying "you can solve SQL injections by not running SQL-injected code".

show 1 reply
wat10000yesterday at 10:46 PM

I can trivially write code that safely puts untrusted data into an SQL database full of private data. The equivalent with an LLM is impossible.

show 1 reply