Hacker News

points by alkonaut 2 days ago | 0 comments

Can’t these detectors be used in the training loop of models?

Also you aren't getting solid gradients, it would be a simple yes/no (or confidence score), as you don't have their model. GANs failed to generalize, even with full access to the discriminator model (providing robust gradients to all weights), its extremely difficult to train in what is basically a reinforcement learning loop over a possibly extremely spiky, nonlinear terrain.

Think of the resources it takes to train good text generators, with perfect knowledge of the next token to generate. Now imagine to trying to do it with a stochastic output of yes/no only (needing to guess proper outputs, and the signal you're getting isn't even deterministic / consistent). You don't even have the distribution over output tokens, you only have yes/no based on the tokens you did generate (a far weaker signal).

[–] JacobAsmuth 2 days ago

People have tried it, it doesn't work.

[–] bobajeff 2 days ago

Which people? I'm no AI researcher but I believe basically all GANs employ a discriminator which basically to me it sounds like this is.

[–] dwohnitmok 2 days ago

I don't know about Pangram's viability as a discriminator but I can tell you as someone who has recreationally trained GANs that they're really really finicky to train and training fails in all sorts of inscrutable ways. It wouldn't surprise me if even though in theory you could do a GAN-style form of training with Pangram, in practice it might actually be very difficult.

[–] treyd 2 days ago

Modern diffusion models aren't trained like GANs. GANs failed to scale and generalize. Diffusion models do sometimes use Variational Auto-encoders (VAEs), which are a similar structure but which functions differently.

[–] XTXinverseXTY 2 days ago

In theory yes, but likely not economical for the slop arbitrageur

It is not a lucrative business and they are not clever people to begin with