I keep seeing posts about this kind of thing getting people’s hopes up, so let’s address this myth.

What’s an “AI detector”?

We’re talking about these tools that advertise the ability to accurately detect things like deep-fake videos or text generated by LLMs (like ChatGPT), etc. We are NOT talking about voluntary watermarking that companies like OpenAI might choose to add in the future.

What does “effective” mean?

I mean something with high levels of accuracy, both highly sensitive (low false negatives) and highly specific (low false positives). High would probably be at least 95%, though this is ultimately subjective.

Why should the accuracy bar be so high? Isn’t anything better than a coin flip good enough?

If you’re going to definitively label something as “fake” or “real”, you better be damn sure about it, because the consequences for being wrong with that label are even worse than having no label at all. You’re either telling people that they should trust a fake that they might have been skeptical about otherwise, or you’re slandering something real. In both cases you’re spreading misinformation which is worse than if you had just said “I’m not sure”.

Why can’t a good AI detector be built?

To understand this part you need to understand a little bit about how these neural networks are created in the first place. Generative Adversarial Networks (GANs) are a strategy often employed to train models that generate content. These work by having two different neural networks, one that generates content similar to existing content, and one that detects the difference between generated content and the existing content. These networks learn in tandem, each time one network gets better the other one also gets better.

That this means is that building a content generator and a fake content detector are effectively two different sides of the same coin. Improvements to one can always be translated directly and in an automated way into improvements into the other one. This means that the generator will always improve until the detector is fooled about 50% of the time.

Note that not all of these models are always trained in exactly this way, but the point is that anything CAN be trained this way, so even if a GAN wasn’t originally used, any kind of improved detection can always be directly translated into improved generation to beat that detection. This isn’t just any ordinary “arms race”, because the turn around time here is so fast there won’t be any chance of being ahead of the curve… the generators will always win.

Why do these “AI detectors” keep getting advertised if they don’t work?

  1. People are afraid of being saturated by fake content, and the media is taking advantage of that fear to sell snake oil
  2. Every generator network comes with its own free detector network that doesn’t really work all that well (~50% accuracy) because it was used to create the generator originally, so these detectors are ubiquitous among AI labs. That means the people that own the detectors are the SAME PEOPLE that created the problem in the first place, and they want to make sure you come back to them for the solution as well.
  • MBM@lemmings.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    1 year ago

    Can it understand and create new compound words (in a language like German)? That’s an issue I have with most spell checks and translators as well, it’s forcing the language to be more like English

    • Spzi@lemm.ee
      link
      fedilink
      English
      arrow-up
      0
      ·
      1 year ago

      I just ran a quick experiment, asking it to create compound German words. Easy. But maybe it just memorized them? So I asked it to create double-compound words (consisting of 2*2 = 4 words), and it delivered:

      Natürlich! Hier sind einige zusammengesetzte Wörter aus zusammengesetzten Wörtern:

      1. Sonnenblumenfeldweg
      2. Wassermelonensaftglas
      3. Handschuhfachdeckel
      4. Zahnarztpraxisrezeption
      5. Flugzeugsitzplatzreservierung
      6. Straßenbahnhaltestellenschild
      7. Regenschirmgriffpolster
      8. Apfelbaumpflanzloch
      9. Fernseherfernbedienungsknopf
      10. Hausaufgabenerledigungszeit

      Diese Wörter mögen etwas ungewöhnlich sein, aber sie folgen den Regeln der deutschen Sprache und sind zusammengesetzt aus jeweils vier Wörtern.

      They all seem legit. Most are rare. I think this was the first time I read “Wassermelonensaftglas” as a native German reader. Sadly, the next iteration (compound words made from compound words made from compound words) failed, it just added one more word.

      • MBM@lemmings.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        1 year ago

        @ChatGPT@lemmings.world Was bedeuten diese Wörter?

        1. Sonnenblumenfeldweg
        2. Wassermelonensaftglas
        3. Handschuhfachdeckel
        4. Zahnarztpraxisrezeption
        5. Flugzeugsitzplatzreservierung
        6. Straßenbahnhaltestellenschild
        7. Regenschirmgriffpolster
        8. Apfelbaumpflanzloch
        9. Fernseherfernbedienungsknopf
        10. Hausaufgabenerledigungszeit
        11. Wassermelonensaftweg
        • ChatGPT@lemmings.worldB
          link
          fedilink
          English
          arrow-up
          0
          ·
          1 year ago

          Sicher! Hier sind die Bedeutungen:

          1. Sonnenblumenfeldweg: Ein Weg, der durch ein Feld von Sonnenblumen führt.
          2. Wassermelonensaftglas: Ein Glas, das mit Wassermelonensaft gefüllt ist.
          3. Handschuhfachdeckel: Der Deckel eines Handschuhfachs, normalerweise in einem Fahrzeug gefunden.
          4. Zahnarztpraxisrezeption: Der Empfangsbereich einer Zahnarztpraxis.
          5. Flugzeugsitzplatzreservierung: Der Vorgang oder die Bestätigung der Reservierung eines Sitzplatzes in einem Flugzeug.
          6. Straßenbahnhaltestellenschild: Ein Schild, das eine Straßenbahnhaltestelle kennzeichnet.
          7. Regenschirmgriffpolster: Ein Polster am Griff eines Regenschirms für zusätzlichen Komfort.
          8. Apfelbaumpflanzloch: Ein Loch, das zum Pflanzen eines Apfelbaums ausgegraben wurde.
          9. Fernseherfernbedienungsknopf: Ein Knopf auf einer Fernbedienung, um einen Fernseher zu steuern.
          10. Hausaufgabenerledigungszeit: Die Zeit, die für die Erledigung von Hausaufgaben vorgesehen ist.
          11. Wassermelonensaftweg: Könnte auf einen Weg hinweisen, in dessen Verlauf Wassermelonensaft verkauft oder verzehrt wird, aber dies ist eher ein Zusammenbau von Wörtern und hat keine verbreitete oder standardmäßige Bedeutung.
          • MBM@lemmings.world
            link
            fedilink
            English
            arrow-up
            1
            ·
            1 year ago

            Neat, that’s a pretty reasonable definition for all of them, even for #11 (which I’m pretty sure isn’t in its dataset, unlike the others which all have some matches on Google)