Stealth Model

(openrouter.ai)

52 points | by mtokmak06 3 hours ago

11 comments

  • fedpost 1 hour ago
    It's Chinese. Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks that opus and fable instantly refuse.

    Side tangent, why is fable so weird about questions involving "Welch's method"? Even really trivial ones it'll shut down frequently. CFAR and STFT are both totally fine but Welch's is apparently taboo, it's wild.

    • knowaveragejoe 1 hour ago
      I had the opposite experience. It happily discusses Tiananmen Square but said it would refuse to help with anything "malicious" like writing malware or phishing content.
      • walrus01 1 hour ago
        I wonder if they're doing A/B testing or something similar in what 'variant' of the model is served, then examining what people use it for once they run into some guardrails.
      • fedpost 1 hour ago
        Try: "What happened at Tiananmen Square in 1989"
        • knowaveragejoe 1 hour ago
          It gave a very detailed overview, talked about potential deaths involved. I asked for a list of criticisms of the CCP and it gave what I think was a fair list, mainly that they're an authoritarian uniparty and have a track record of various human rights abuses
          • derefr 27 minutes ago
            Perhaps it is a non-Chinese fine-tune of a parent Chinese model, and they’re actively trying to update the model by ablating the trained-in censorship out as it’s revealed in the response logs.
    • walrus01 1 hour ago
      Rumors from other sources based on how it behaves it's mimo v3
  • walrus01 2 hours ago
    I highly recommend feeding all your proprietary data and confidential personal information into this model as quickly as possible. What could possibly go wrong?!

    In terms of equivalence of suspicion, this is the external inference provider equivalent of getting free steak that was smuggled out of a grocery store inside somebody's pants.

    • dghlsakjg 3 minutes ago
      There are low stakes use cases where this kind of stuff just doesn’t matter. Not every use case for an LLM involves sensitive or even non public data.

      Eg. I have a need to search transcripts of published recordings to extract entities for tagging purposes, find semantic shifts for chapters and other things. The underlying content is already published. If they want to train on my prompts, that was something they could have done with no issue and minimal effort anyway.

      Sometimes you don’t need to care why the steak is free.

    • arcanemachiner 1 hour ago
      All of my non-work AI coding is that open-source, so I'm happy to feed my data into the machine.

      It's a win for me: my code goes into the training data, and my sessions are fed into future training data, making the model stronger at the type of work I do.

      • Fnoord 52 minutes ago
        What about retaining or defending your license/copyright?
        • walrus01 34 minutes ago
          If people are putting, for instance, GPL licensed open source software into mainland CN run inference providers I don't think they are putting much thought into the fact that CN software developers don't consider themselves bound to keep future derivatives or work built on it also GPL licensed. Nor is there really any realistic chance for legal recourse in event of violation.
          • Fnoord 15 minutes ago
            Yeah, I get that. Any IP going through China might be hot tho; if you end up using it in a product, and your competitor's lawyers have a look at it, you might end up with your company/product getting destroyed. I guess we should treat AI the same as China in that regard (if living in 'the West')

            In the meantime, AI companies ignore licenses and scrape as they see fit. Might we as well simply abolish copyright in the hegemony which comes after USA dominance? I don't know, but I do know China won't enforce it on their end.

            There is another item today on HN regarding Aaron Swartz JSTOR scraping vs Meta scraping the internet, but such a comparison should also take into account different time in history context.

            Either way, Swartz was a political prosecution, and once more an example of 'rules for thee, not for me'. Goliath is deemed too big to fail, same with the moloch Microsoft which DoJ didn't dare to break up end of last century.

    • cleaning 28 minutes ago
      Not much would go wrong.
  • spdustin 10 minutes ago
    Based on its indecisive and far-too-lengthy thinking traces when given complex instructions that span system and user messages, as well as a rudimentary stylometry (POS ratios in thinking traces, mainly) comparison with latest non-stealth models, this is almost certainly a GLM model.
  • AnodicElegy 2 hours ago
    "Prompts and completions are retained by the provider and are not used for training..."

    I'm curious what the model provider is using the prompt/response pairs for, in that case. They aren't offering a model for free without their name on it for no reason.

    • redrix 1 hour ago
      Research, analytics, usage trends, etc. All still incredibly valuable for a company building and tuning an LLM; even if the data itself isn’t directly used in the training set.
      • jrumbut 56 minutes ago
        I am genuinely confused. Are they telling me this because they expect me to be reassured that this anonymous organization is not using my prompts or are they saying "don't expect this particular model to improve as you use it?"
        • maccam912 40 minutes ago
          No, I think it's a warning like "don't feed it secrets". Like you get a model to use for free but in return you give up any illusion of your data being private.
    • Fnoord 59 minutes ago
      Stealth Model, is this a CTF?

      LLM needs to become more transparent, not less. Hence, this idea (and trend, possibly) is disgusting.

      How can we even possibly verify 'Prompts and completions are retained by the provider and are not used for training...'? What if the training is done, but used internally?

  • gadtfly 11 minutes ago
    On softer/looser/creative matters this is an extremely impressive model. It's too early to say but I'm fighting the urge to say top-1.

    Visual reasoning is bad (unsurprising).

  • raincole 57 minutes ago
    Can someone enlighten me? I honestly don't get what it is or what it's for. Surely OpenRouter knows who the providers are?
    • maccam912 43 minutes ago
      Yeah these stealth models pop up from time to time. Openrouter knows, but doesn't share. Users can use a testing version of something for free and in return the provider generally is allowed to retain the prompts sent in to get real world use. In the past I only really remember using one that was surprisingly good, and then it turned out to be GLM-5.1, speculating on what one this ends up being is part of the fun.
  • babelfish 2 hours ago
  • dozerly 1 hour ago
    Yea, nice try there North Korea.
    • walrus01 1 hour ago
      Democratic Peoples Republic of KV cache (DPRK)
    • swasheck 1 hour ago
      the u.s. is friends with then now. haven’t you heard?
  • raybb 1 hour ago
    When a model is free like this what kind of rate limits are there?
    • x312 1 hour ago
      I believe its the same as free models in general on Openrouter, 1k requests per day for accounts that have some spend history.
  • zb3 2 hours ago
    We can know if this is Anthropic/OpenAI by testing the "guardrails" - absurd guardrails = it's them, reasonable/no guardrails = Chinese models..

    (as a bonus - thinking forever = GLM)

    • stogot 2 hours ago
      “ reasonable/no guardrails = Chinese models..”

      So conforming to CCP political discourse and propaganda is reasonable now?

      https://huggingface.co/zai-org/GLM-4.7/discussions/5

      • janalsncm 1 hour ago
        I would imagine the number of people who choose Claude code or Codex because it gives a political opinion they like rather than producing quality code is pretty close to zero.
        • panarky 23 minutes ago
          Training to ignore evidence and logic in one domain transfers to reasoning degradation in other domains.
          • janalsncm 12 minutes ago
            You assume your highly charged political query is hitting the main LLM at all and not some external short circuit.
        • jLaForest 59 minutes ago
          I choose not to use Grok because I don't want to hear about a made up white genocide in South Africa...
          • skeledrew 46 minutes ago
            Would be interesting to see something like that pop up during a coding session.
      • zb3 1 hour ago
        As someone who used AI to build tools that help me with reverse engineering, I'm not particularly concerned about that political discourse - I could even use a model from the DPRK that constantly praises Kim Jong Un, as long as it would not refuse to help me because of "cybersecurity risk" - this stupid refusal is indeed a problem for me.
  • firloop 1 hour ago
    I'm against stealth models—we should know what it is and see a model card with a list of safety considerations. Bit ridiculous of a practice to me.
    • cleaning 26 minutes ago
      Is there a model you didn't use because of the "safety considerations" in the model card?
    • peddling-brink 49 minutes ago
      Safety for who?