News for hackers. Stuff that matters.
Re:Our decision on Cursor following its acquisition by SpaceX by bentt on Friday August 28, 2026 @11:22PM (#49486604)
I'd need to have a problem I couldn't solve with current models for my eyes to wander.
Re:Our decision on Cursor following its acquisition by SpaceX by znnajdla on Friday August 28, 2026 @11:51PM (#49486721)
Yeah I haven’t had a problem yet which was too difficult for Fable to solve. I do have problems which Sol does not do well on. But if I could get Fable-level intelligence faster/cheaper and less restricted, that’s all I need.
Re:Our decision on Cursor following its acquisition by SpaceX by cheeze on Saturday August 29, 2026 @01:04AM (#49487020)
Fable is great minus it's annoying writing style. It's nowhere near as bad as Opus 5 but it's very "AI trope-y" even with heavy steering. I can spot the writing immediately.
Re:Our decision on Cursor following its acquisition by SpaceX by muddi900 on Sunday August 30, 2026 @07:53AM (#49497887)
Asking your models to follow the google developer guidelines is angood way to get good responses from them.

https://developers.google.com/style/highlights

Re:Our decision on Cursor following its acquisition by SpaceX by akmarinov on Saturday August 29, 2026 @12:46AM (#49486957)
What if it’s cheaper too?
Re:Our decision on Cursor following its acquisition by SpaceX by dakolli on Saturday August 29, 2026 @12:59AM (#49487004)
Yeah not sure why everyone thinks they need a PhD lvl assitant to build their slop SaaS when an open source model that is 100x cheaper, and 3x faster and arguably still "PhD" level assitant could also build their slop SaaS.
Re:Our decision on Cursor following its acquisition by SpaceX by hand2note on Sunday August 30, 2026 @05:32PM (#49503044)
It like saying before the ai era that you don’t have a problem you can’t solve without ai