Post #1034126
2026-04-02 22:33 UTC
The hilarious part about people writing "skills" or prompts is that no matter how much they write… they're still interfacing with nondeterministic models
"You **must never** `rm -rf /folder` ever!"
1. There's no guarantee this won't happen (only a decreased likelihood)
2. This has now added something it shouldn't do as part of its context… potentially increasing the likelihood of it happening
This is fine
Replies (2)
-
@me1000@mastodon.social 2026-04-02 23:08
@b3ll relying a prompt for security is wrong, of course, but that’s not the point of adding the instruction. And it’s not like humans are particularly good at following instructions. 😆
-
@ghalldev@mastodon.social 2026-04-03 02:29
@b3ll In my fairly limited experience it seems that trying to rein in these LLMs generally just makes them more unreliable. The only rule I could reliably get it to follow was to not run any build commands and it would brag about not running build commands every time it did anything. 😂