The vram usage is: niri = ~163mb

--

noctalia = ~221mb ashell = ~2mb ironbar = ~10mb

TLDR: coding is not solved.

I have 2 projects, one it's a distributed platform, the other one is a general processing engine with an inner workflow engine; Since gpt 5.2 I've tried new models to work in these codebases where the code is of good quality and every time I gave the model a slice of work instead of a single step from that slice the code, the tests, the comments, the docs and everything else has been suboptimal, unmaintainable, complex, bloated and just slop, unless I micro-manage and do many passes.

As a dev when you make a change you consider the broad picture, you consider the user, the codebase, future requirements, maintainability, performance, your team's understanding and some of these you do unconsciously. We are slow but that's for multiple good reasons, you push the organization/understanding forward not just loc of that specific project. I can't count how many PR notes or comments I've added considering teammates or just for a specific team member.

I don't see any way forward for an LLM to reach that unless it reaches general problem solving, my definition of GAI that could tackle software development or "coding" would be a model that doesn't require additional pretraining to solve new tasks or improve how it solves tasks in the future, it would just learn as it's going.

Can everything I mentioned be solved with current generation of LLMs and lot's of markdown and gates? Maybe... but the amount of effort required would be similar to the effort an expert system (pre-llm AI) would require to embed the rules, evolve them, check them everytime... which would require billions or trillions of tokens.

---

off: I really like the discussions around how to prevent slop and bloated code as it's something it would benefit coding even without LLMs and can fit as another piece of automated infra for checking and ensuring code quality, I hope something materializes.

Some of them look good at a quick glance, polished readmes, recent activity, commit history, features lists..etc. But when you look at the code they turn surprisingly bad, surprisingly fast, low effort, low quality, unmaintainable messes of patches that break compatibility every other version. AI has made this 100x worse.

In the past, if a project had a relative high number of gh stars and activity in relation to the niche that would mean the project had some standard of quality/potential/efficacy and you could review 1-3 projects, basically it acted as a good first filter, today there are hundreds.

How do you find the signal in the noise, tips/tricks? Some heuristics I use: multiple contributors, less is more when it comes to commits per day, if the author uses AI a small signal is if they limit/block acceptance of PRs, codeberg or outside github repos and of course AGENTS/CLAUDE.md, especially CLAUDE.md.

Curious what signals you found useful, especially ones that are difficult to game and can be semi-automated so at the end you only review the fewest number of them left? loc, file count, other registries?

Comments URL: https://news.ycombinator.com/item?id=49580521

Points: 2

# Comments: 0

From what I see helix has stopped being developed, probably ppl think its done but i feel its half baked without a plugin system and tons of basic functionality missing.

off: I'm working on my spare time on a code mode lisp alternative (great opportunity to learn lisp) and might switch to it fully as long as I built some simple evals (I'm concerned about token usage, which is why i forked pi the first time)

Is that correct?

https://harness.eveid.com/lazy-harness-cost-simulation

ignore the numbers except the classic and keep in mind that classic is based on pi with the only change limiting tool output to 10kb

https://harness.eveid.com/lazy-harness-cost-simulation

* I built this for getting an initial estimate between different checkpoint/ compaction methods for the harness.

It's packed with features, voice mode, browser. I'm not really the target audience..

I've noticed that for me it's much faster to learn by doing exercises targeting the exact thing you need than just trying to apply that to a much bigger chunk of work directly, especially for someone that's a bit of a failing perfectionist.

I was just looking for that and I saw https://github.com/THU-MAIC/OpenMAIC. I haven't tried it as I'm trying a few small experiments to see if I can create a curriculum for a framework with no docs.

The first naive one failed for multiple reasons but mostly because many guardrails are needed and we need a proper process that tracks too many things.

Is no one trying to ship polished things to customers anymore, will each of us have a hacky, bugged version of the same thing with different quirks?

--

My first ever software project even before I worked as a swe had less bugs and frictions than all recent projects where AI was used. Some people like mitchellh seem to know what they are doing (I have not taken a look at ghostty's codebase as it's in zig) so I sometimes get the feeling I'm holding it wrong but in the end everyone around me seems to have similar problems with shipping.