Skip to content

Comment on AI-proof rule

You are viewing one comment and its replies. View all comments · View the comment above

Comments

  • Correct me if I’m wrong, but isn’t that a feature of the harnesses that Chinese tech companies expose, and not in the model itself? And with their tendency to be open weight, it’s often easy to bypass?

    19
    • It’s both. Kinda “in between.”

      The web/app interfaces use keyword detection, and maybe more prefiltering for sure.

      API access generally doesn’t do such aggressive prefiltering, AFAIK. There are some situations where things may be checked after the fact (like using a coding API for non coding things).

      And yes, the LLM weights themselves (like when locally run) do refuse some stuff. But I’ve found them to not be as censored as you’d think; for example I got GLM 4.7 to analyze and criticize a CCP law as “incompatible with the international definition of human rights,” no prompt manipulating or anything. It even went to look up the original Chinese text, and held its critical opinion.

      I haven’t needed a abliterated model in some time.

      But if you push them with some obvious meme topic, of course they will refuse.

      18
    • It’s usually in the weights itself, but abileration is a thing.

      4
      • Yeah as I said, I don’t really know. I’ve not used it at all myself. I mainly recall way back when the first prominent Chinese model came out, a bunch of people were saying that you could bypass the censorship just by self-hosting the model. And I hadn’t heard anything contradicting that since.

        1

Sign in to comment. Sign in