Rather than adding an agents.md file written to stop LLM agents, I’m thinking about putting random comments into my code telling the agent to stop and warn the user, also some comments that are just word salads/non-sequiturs.
Rather than adding an agents.md file written to stop LLM agents, I’m thinking about putting random comments into my code telling the agent to stop and warn the user, also some comments that are just word salads/non-sequiturs.
I wouldn’t trust trying to poison anything that will be lost in compile time.
If I was an AI Bro looking to take your stuff, I’d decompile and recompile a few times to remove most of the surprises you’ve got for me.