News for hackers. Stuff that matters.
Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released by Razengan on Monday August 17, 2026 @08:55AM (#49330074)
For the last 2 weeks I've been trying to get Codex to "outpaint" a wonderful image it generated as placeholder art for a level background.

After I increased the game's resolution, I asked it to increase the image's size while keeping the same scale and existing content, and gosh, it constantly keeps getting something wrong no matter what I tell it, even on Sol Max with the $100 Pro subscription.

An organically-grown meat-based pixel-artist could have recreated the image and more within 2-3 days, in exchange for food and shelter.

Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released by dev_hugepages on Monday August 17, 2026 @09:35AM (#49330610)
I'm unsure why you're using an LLM to generate images. Don't we already have models (some made by the same company) that do this?
Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released by sscaryterry on Monday August 17, 2026 @09:10AM (#49330260)
> it constantly keeps getting something wrong no matter what I tell it

This 100%

Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released by thatcat on Monday August 17, 2026 @08:59AM (#49330122)
did you try segmenting it first?
Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released by Razengan on Monday August 17, 2026 @10:26AM (#49331564)
At first I intended to create a tileset and asked it for several variations of what a hypothetical tilemap created from the planned tileset would look like.

The previews it generated were amazing but wouldn't really be possible as a grid-based tilemap, with lots of clusters and overlaps of elements of varying sizes.

So I just decided to use the preview as a static scrolling background, but it's been a pain to get it to add more content around the edges that still tiles with the existing image at the same scale.