lvxferre , 20 hours ago

It doesn’t need to be filtered into human / AI content. It needs to be filtered into good (true) / bad (false) content. Or a “truth score” for each.

That isn’t enough because the model isn’t able to reason.

I’ll give you an example. Suppose that you feed the model with both sentences:

1. Cats have fur.
2. Birds have feathers.

Both sentences are true. And based on vocabulary of both, the model can output the following sentences:

1. Cats have feathers.
2. Birds have fur.

Both are false but the model doesn’t “know” it. All that it knows is that “have” is allowed to go after both “cats” and “birds”, and that both “feathers” and “fur” are allowed to go after “have”.