[redredrobot]

So his argument is that the text clearly maps to concepts in the latent space, but when composing them the results are unexpected, so it isn't language? Why isn't this better described as 'the rules of composition are unknown'?

[rcoveson]

That framing is worse because it hides an assumed conclusion, i.e. that there are rules of composition.

[redredrobot]

But don't we already know that composition exists in DALL-E? Don't the points shown in the tweet indicate that some form of composition exists? The 3D renders are clearly render-like, the painting and cartoons are clearly in the appropriate style.