News for hackers. Stuff that matters.
Re:OpenCode 2.0 by illiac786 on Thursday October 15, 2026 @02:18PM (#50107899)
> A commit born from "Claude, please make the installer look sick as fuck with loading bars and stuff" will always be preferred by the developers over a commit that reverts such a change for a 10 MB drop in memory use.

Not my experience. YMMV

> I had always imagined that the advent of LLMs developing human-level coding abilities, combined with the high hardware prices as a result of it, would act as a forcing function to inspire a new generation of ultra-performant, bloat-free open software.

I mean, faster and better hardware has never resulted in more efficient software, I really didn’t expect it to be any different here.

Re:OpenCode 2.0 by emmettm on Saturday October 17, 2026 @08:16PM (#50136557)
>faster and better hardware has never resulted in more efficient software, I really didn’t expect it to be any different here.

I agree with this.

By "high hardware prices", I am implying that we are not getting faster and better hardware.

NVidia halted 5090 production yesterday. As a consumer, where can I buy this faster and better hardware you speak of?

Re:OpenCode 2.0 by illiac786 on Saturday October 17, 2026 @11:22PM (#50137631)
Sorry, my comparison is not perfect.

I was comparing faster hardware (Wirth's law) with better LLM, which is actually more the Jevon’s paradox.

My point was along the line of: Making something easier has never caused that something to be executed more efficiently.