News for hackers. Stuff that matters.
Re:Coding Is Not Solved by bitwize on Monday September 28, 2026 @11:38AM (#49879745)
Tell me you're not using a frontier model without telling me you're not using a frontier model
Re:Coding Is Not Solved by 0c3ca83 on Monday September 28, 2026 @11:54AM (#49880039)
Tell me you never once bothered to look at the generated code without telling me you don't look at the generated code.

Luajit is under 80,000 lines of code.

Re:Coding Is Not Solved by paganel on Monday September 28, 2026 @11:47AM (#49879904)
Where's the great software, then? I'm genuinely asking: where is it? Because I can't find it, and it's been close to a year since AI for programming has started to take off.
Re:Coding Is Not Solved by dawnerd on Monday September 28, 2026 @11:55AM (#49880049)
In fact, a lot of the once great software that's switched to AI driven development has gotten worse.
Re:Coding Is Not Solved by cat-snatcher on Monday September 28, 2026 @12:07PM (#49880245)
For example?
Re:Coding Is Not Solved by 0c3ca83 on Monday September 28, 2026 @12:47PM (#49880851)
Google.
Re:Coding Is Not Solved by cat-snatcher on Monday September 28, 2026 @01:02PM (#49881048)
It was going downhill way before AI.
Re:Coding Is Not Solved by intrikate on Monday September 28, 2026 @01:38PM (#49881566)
That's true, but also doesn't prevent the accelerated decay that it seems to be undergoing since AI hit the scene en masse a few years ago.
Re:Coding Is Not Solved by dawnerd on Monday September 28, 2026 @01:37PM (#49881544)
Clickup. Windows. Github, VSCode...

Could be argued they were going downhill before but it's a much faster decline since 2023-ish

Re:Coding Is Not Solved by necovek on Monday September 28, 2026 @03:03PM (#49882855)
Somebody posted that GitHub status summary: in ten years, they averaged 10 incidents per month — this includes the last 12 months. In the last six months, average is 22.
Re:Coding Is Not Solved by whateveracct on Monday September 28, 2026 @02:06PM (#49881963)
i have unlimited tokens and i throw Fable / Astra at everything. They suck ass still for anything nontrivial. I could commit that garbage but if I kept doing it, I will end up with a ball of mud only Fable / Astra can grok..convenient for Dario and SamA..
Re:Coding Is Not Solved by necovek on Monday September 28, 2026 @03:00PM (#49882809)
I've asked Codex with GPT 6 Astra to *review" a one time benchmarking script for any mistakes (built by Claude Code using Opus 5.5) and it refactored the shit out of it claiming all sorts of stuff without even asking about the context in which it was developed.

If I was to employ them to review the code without giving each the same baseline multi-page prompt, they go into endless loop of "improvement" with no end goal in sight.

More and more frequently, I instruct frontier models to stop and go back to the task at hand.

Re:Coding Is Not Solved by perrygeo on Tuesday September 29, 2026 @04:07PM (#49899580)
Frontier models are subjectively worse at this, in my experience. Very intelligent but very prone to expanding scope. I need to spend more time prompting to get good results. Maybe I'm just working on boring stuff that doesn't require "frontier" intelligence?