Re:Instant 1.0, a backend for AI-coded apps
by storus on Thursday April 09, 2026 @10:43PM
(#47712996)
With local inference on pretty decent local models we have nowadays (Qwen-3.5 and better) it's not much of a concern anymore.
[ Parent
| on HN ]
Re:Instant 1.0, a backend for AI-coded apps
by Bishonen88 on Friday April 10, 2026 @03:12AM
(#47714650)
what percentage of people is using local models for anything serious? I reckon single digits if even that. And for a corporate work environment, probably close to 0.
Re:Instant 1.0, a backend for AI-coded apps
by walthamstow on Friday April 10, 2026 @08:01AM
(#47716786)
Sure, if you've got a £5k laptop
Re:Instant 1.0, a backend for AI-coded apps
by IncreasePosts on Friday April 10, 2026 @03:07PM
(#47722299)
Sure it is - there's still an opportunity cost of spending tokens(time/energy) creating a library from scratch vs using a preexisting well understood API.