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
[–] [S] 1 point 3 days ago

I already do some pseudo-namespacing, like gl_variableName, which makes it faster for me to look up rendering stuff, and will be extra useful the moment I'm implementing the other renderer(s).

  • source
  • parent