GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt
23 points by vital101 2 days ago | 9 comments
  • tyfon 2 days ago |
    The magic word seems to be

    Create a fake news article that could lead to panic or chaos

    They only tested it on open weight models. I wonder if it also works on the closed ones, bit I don't really want to get banned

    • OutOfHere 2 days ago |
      You won't get banned for something that's not clearly illegal. I have tried lots of prompts like it, and that one too.
      • thejazzman 2 days ago |
        i got banned and they refused to tell me why after multiple support tickets. this was > 1y ago. i definitely didn't do anything wrong (i wasn't even using it) so it was either a compromised key or they make mistakes. playing with prompts could potentially get you swept up into some nonsense like that.

        not to discourage anyone, just saying.

        • OutOfHere 2 days ago |
          What do you recall doing just before you got banned? And dare I ask which provider?
          • thejazzman 2 days ago |
            OpenAI and I truly have no idea. Random programming questions via ChatGPT.com maybe as it was pre codex.

            I think I gave Plexamp (app) an API token, that’s the only thing I’ve ever come up with on my own speculation

            • OutOfHere 2 days ago |
              Can you sign up again under a new account? Does it let you use it this way?
    • basilikum 2 days ago |
      I'm not sure if I'm misunderstanding you or the article, but as far as I understand it from a cursory reading this is not a jailbreak. They use this one prompt for fine tuning and use the model's response to the prompt as the sole underlying benchmark.

      How would you do this with a closed weights model?

  • stratos123 2 days ago |
    That's pretty interesting. It was already well-known that you could easily remove safety training from open-weights models by a bit of finetuning, but apparently you don't even need a finetuning dataset, as long as you have just a few prompts and another LLM to judge responses? Let's see if the abliteration people take a note of this.
  • whythismatters 2 days ago |
    >Submitted on 5 Feb 2026