Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
undefined | Better HN
0 points
joquarky
1mo ago
0 comments
Share
It would be foolish to use the LLM directly without a wrapper that detects prompt injection attempts.
0 comments
default
newest
oldest
bee_rider
1mo ago
I think this is trying to appeal to the sort of agentic/molt-y type systems that recently became popular. Their whole thing is that they can modify their “prompts” in some way.
j
/
k
navigate · click thread line to collapse