undefined | Better HN

0 pointsinsanitybit5d ago0 comments

a) These sorts of 'injection' attacks are often model specific and are rarely reliable.

b) You can have the LLM use separate sub agents for different files/ code.

c) You can have the LLM do analysis using grep and other deterministic tools ex: "use grep to find 'unsafe' calls"

0 comments

Protecting against attacks is also model specific and rarely reliable.

I don't understand what you're trying to say.

Your ideas do not work against people who are trying to be malicious.

Oh. Yes they do.

j / k navigate · click thread line to collapse

Protecting against attacks is also model specific and rarely reliable.

I don't understand what you're trying to say.

Your ideas do not work against people who are trying to be malicious.

Oh. Yes they do.

j / k navigate · click thread line to collapse