News for hackers. Stuff that matters.
Re:DeepSeek v4 by simonw on Friday April 24, 2026 @02:48AM (#47886512)
I tried that for the GPT-5 launch - a self-improving loop that renders the SVG, looks at it and tries again - and the results were surprisingly disappointing.

I should try it again with the more recent models.

Re:DeepSeek v4 by torginus on Friday April 24, 2026 @04:47AM (#47887468)
I see, thanks. I guess most current models are not yet trained for this loop.

Could you please try with Opus 4.7? I think there's a chance of it doing well, considering the design/vision focus.