[Aurornis]

We're in the messy transition period where our old indicators of a promising GitHub project are too easily replicated by someone letting Claude Code run for a few days.

A year ago it would have taken someone months of nights and weekends effort to get this much code up and running. That person would have developed a good intuition for the architecture and where it should go.

Now Codex or Claude can bang it out in a couple days. You can try to have it do spec documents, code reviews, and cleanup passes but with today's tools these projects reach a point where it's just a swirling mess of pieces duct taped together in a way that passes tests. In my experiments, you quickly reach a point where the usable context depth (which is less than the 1M limits) keeps overflowing before you can get usable refactors in, and you're just going in circles. I know it's theoretically possible to avoid these problems, but in practice you get spaghetti projects like this.

[elcritch]

I don’t know, GPT-5.5 has been very effective for me. It’s not perfect but the quality of refactoring it can do is awesome.

Previous models both GPT and Claude would struggle with the larger picture more. Pretty quickly they’d do one off hacks. Eventually they’d code themselves into a wall if you weren’t careful.

Haven’t hit that wall with GPT-5.5 yet. New changes or improvements on a GUI library I’m building seem to be constant in time per feature.

Though I’m talking only 10k’s of LOC. Also I’m using Nim which is both strongly typed and concise.

[willtemperley]

> Haven’t hit that wall with GPT-5.5

I’m seeing a similar improvement with Opus 4.8, which is acting like an engineer that cares about correctness. The harder the problem the better it seems to do.

I think a golden age of software is just starting for indie software. It’s just going to take a while to see the first really good results.

[SkiFire13]

This is what people say after every new model is released though.

[reactordev]

You have to drink the koolaid if you want to keep tokenmaxxing

[elcritch]

Who cares about tokens?

I'm wanting to build pieces of software that I've been wanting and often working on for years. These new models are making it possible for me to scale my work to build it.