← Back to context Comment by joquarky 6 days ago It would be foolish to use the LLM directly without a wrapper that detects prompt injection attempts. 1 comment joquarky Reply bee_rider 6 days 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.
bee_rider 6 days 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.
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.