Tell me you're not using a frontier model without telling me you're not using a ...

paganel · 2026-09-28T15:47:35

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.

dawnerd · 2026-09-28T15:55:08

In fact, a lot of the once great software that's switched to AI driven development has gotten worse.

cat-snatcher · 2026-09-28T16:07:29

For example?

dawnerd · 2026-09-28T17:37:28

Clickup. Windows. Github, VSCode...

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

necovek · 2026-09-28T19:03:21

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.

0c3ca83 · 2026-09-28T16:47:15

Google.

cat-snatcher · 2026-09-28T17:02:27

It was going downhill way before AI.

intrikate · 2026-09-28T17:38:43

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.

whateveracct · 2026-09-28T18:06:10

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..

necovek · 2026-09-28T19:00:36

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.

perrygeo · 2026-09-29T20:07:08

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?

0c3ca83 · 2026-09-28T15:54:36

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.