If I'm not mistaken ROOM (ObjecTime, Rational Rose RealTime) was also heavily based on it. I worked in a company that developed real time software for printing machines with it and liked it a lot.
I think that's very difficult. To detect prompts you need to have natural language understand and therefore probably another detection LLM which is itself probably vunerable to prompt injection.
I also use niche questions a lot but mostly to check how much the models tend to hallucinate. E.g. I start asking about rank badges in Star Trek which they usually get right and then I ask about specific (non existing) rank badges shaped like strawberries or something like that. Or I ask about smaller German cities and what's famous about them.
I know without the ability to search it's very unlikely the model actually has accurate "memories" about these things, I just hope one day they will acutally know that their "memory" is bad or non-existing and they will tell me so instead of hallucinating something.
For me it's mostly about indentation / scope depth. So I prefer to have some early exits with precondition checks at the beginning, these are things I don't have to worry about afterwards and I can start with the rest at indentation level "0". The "real" result is at the end.
This always scared me because I don't even know what counts as shaking.
Can you accidentally shake a baby? Can my 2 year old daughter get shaken baby syndrome when older children on an inflatable castle with her jump and bounce too wild around her (she can't jump yet but loves the bouncing)? I've also often seen parents throw their children a bit in the air and then catch them. The children like it and laugh.
I'm not even speaking of law and police but medically. Can this seriously hurt my daughter?