> ... than they ever cared about democratization of the immense power of these models.
I thought they're pretty explicit about the ethical argument for limiting full public release? They'd say that these models are too powerful to release on an unsuspecting world. Google results are already SEO spammed to death and GPT'd SEO spam would make it far worse. Or Nigerian prince scammers and catfishers could use ChatGPT to hold on long trust-building conversations with infinite would-be victims instead of being limited by the number of English speaking human scammers they can hire. The nefarious use cases go on and on.
So I think OpenAI's ethical argument is that this approach reduces potential harm. By keeping it private but still making it available behind an API they can more slowly prepare the world for the eventual AI onslaught. Like the investments in ChatGPT detectors we've been seeing and just general awareness that this capability now exists. Eventually models this powerful will be democratized and open-sourced, no doubt, but by keeping them locked down in the early days we'll be better prepared for all the eventual nefarious uses.
Of course, it's a bit convenient that keeping the models private and offering them as an API also grants them a huge revenue opportunity, and I'm sure that's part of the equation. But I think there's merit to the ethical rational for limiting these models besides just pure profit seeking.
The Ethics argument is a weak one, and we have very recent proof to show it's a useless argument at best: we saw the how both Dall-E and Stable Diffusion affected the world.
The first was kept behind close doors because "muh ethics" and the second one was released in the wild. The world hasn't gone down under, but the technology iteration rate in this area has improved manyfold since Stable Diffusion came out.
I thought they're pretty explicit about the ethical argument for limiting full public release? They'd say that these models are too powerful to release on an unsuspecting world. Google results are already SEO spammed to death and GPT'd SEO spam would make it far worse. Or Nigerian prince scammers and catfishers could use ChatGPT to hold on long trust-building conversations with infinite would-be victims instead of being limited by the number of English speaking human scammers they can hire. The nefarious use cases go on and on.
So I think OpenAI's ethical argument is that this approach reduces potential harm. By keeping it private but still making it available behind an API they can more slowly prepare the world for the eventual AI onslaught. Like the investments in ChatGPT detectors we've been seeing and just general awareness that this capability now exists. Eventually models this powerful will be democratized and open-sourced, no doubt, but by keeping them locked down in the early days we'll be better prepared for all the eventual nefarious uses.
Of course, it's a bit convenient that keeping the models private and offering them as an API also grants them a huge revenue opportunity, and I'm sure that's part of the equation. But I think there's merit to the ethical rational for limiting these models besides just pure profit seeking.