News for hackers. Stuff that matters.

A comment on DeepSeek v4. Parent comment

Re:DeepSeek v4 by avereveard on Friday April 24, 2026 @02:03AM (#47886173)
eh idk. until yesterday opus was the one that got spatial reasoning right (had to do some head pose stuff, neither glm 5.1 nor codex 5.3 could "get" it) and codex 5.3 was my champion at making UX work.

So while I agree mixed model is the way to go, opus is still my workhorse.

[ Parent | on HN ]
Re:DeepSeek v4 by gunalx on Friday April 24, 2026 @05:16AM (#47887671)
I find gemini pretty good ob spatial reasoning.
[ Parent | on HN ]
Re:DeepSeek v4 by avereveard on Friday April 24, 2026 @05:44AM (#47887882)
Yeah but gemini has a hard time discussing about solutions it just jump to implementation which is great if it gets it right and not so great if it goes down the wrong path.

Not saying it is better or worse, but the way I perpersonally prefer is to design in chat, to make sure all unknown unknown are addressed

[ Parent | on HN ]