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.

you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 3 days ago

Just speculating:

What about tons of spaghetti code? Get an LLM to write 5000 lines just to add a couple numbers or something. Maybe even LLM-up a fancy splashy website to sell the "math library".

  • source