News for hackers. Stuff that matters.

A comment on Is DALL-E 2 ‘gluing things together’ without understanding their relationships?. Parent comment

Re:Is DALL-E 2 ‘gluing things together’ without understandin... by IIAOPSW on Thursday August 04, 2022 @10:50AM (#32343655)
That's not a word game at all. To know what a giraffe is is to be able to understand the implications of being informed that something is a giraffe. Dalle would never assume on its own that "a giraffe close to a low flying helicopter" could be very dangerous for the giraffe, but "a horse close to a low flying helicopter" is safe.
[ Parent | on HN ]
Re:Is DALL-E 2 ‘gluing things together’ without understandin... by nextaccountic on Thursday August 04, 2022 @12:52PM (#32345328)
> Dalle would never assume on its own that "a giraffe close to a low flying helicopter" could be very dangerous for the giraffe, but "a horse close to a low flying helicopter" is safe.

Are you sure? (Can someone run down those prompts?)

Dall-e might be able to make those relationships in the latent space

[ Parent | on HN ]
Re:Is DALL-E 2 ‘gluing things together’ without understandin... by gattilorenz on Thursday August 04, 2022 @05:56PM (#32348801)
> Are you sure?

Considering Dall-e has problems painting "a red cube on top of a blue cube" [1] and all kind of simple spatial relations, I'd say it's a fair shot.

[1] As reported by OpenAI, but there are also some prompts by Gary Marcus et al. (https://arxiv.org/abs/2204.13807) showing this, and it's trivially simple to find other very simple cases like these

[ Parent | on HN ]