News for hackers. Stuff that matters.

A comment on Introducing Images 2.6. Parent comment

Re:Introducing Images 2.6 by minimaxir on Wednesday November 04, 2026 @09:59PM (#50374591)
> Think of the problems AI has with creating appetizing food imagery, for example.

The memetic ugly food can be controlled and mostly filtered out with prompt engineering. Here's a quick ad hoc test example which (hopefully) uses the new model: https://chatgpt.com/share/6aebf030-9d38-83e8-a103-3509883905...

First image is fine, but attempts to make it more wacky turn it to the AI food slop. So then followup prompts deslopify it, mostly successfully.

[ Parent | on HN ]
Re:Introducing Images 2.6 by phoghed on Wednesday November 04, 2026 @11:59PM (#50375391)
tbh it got worse every time, the first one is the best lol
[ Parent | on HN ]
Re:Introducing Images 2.6 by demibabs on Thursday November 05, 2026 @12:30AM (#50375574)
Eh, looks like slop still in my opinion. The evenness and density of the teeth especially stands out to me as uncanny.
[ Parent | on HN ]