You don't use AI in your project? Add your project here or reply to this page: https://noailist.org/add-your-project/
"Made without AI"

you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 1 day ago (1 child)

Probably no way to do something like that and be imperceptible to humans. Could probably find ways to mangle variable names adversarially, but that would also make it harder for humans. The best thing would probably be trying to do reliable bot detection, then serve the bots adversarially constructed text that *looks" plausible, but is nonsense/broken. I've heard about "tar pits" and "markov tarpits;" I don't know if they try to make the content look legitimate and/or adverserially construct the content to try to maximize damage during training.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 1 day ago*

    Tar pits are cool, but you can't really put one in front of your codebase when you have it publicly hosted in GitHub or Codeberg or similar.

    There are a lot of cool ways you can fuck up code for an LLM and still have it compile just fine... but the problem is that this also makes the codebase a complete nightmare for humans to work on. The real trick is to find a way to make the obfuscation reversible... but in a way that only a human can reverse it. That's the hard problem, and I'm not sure it's solvable.

  • source
  • parent