Hacker News

Favorites Setup
Comment by yogthos | original | ZCode – Harness for GLM-5.2
[−]yogthos · 2026-07-02 Thu 02:04 UTC · link
This is precisely what I've been working on targeting with https://dirge-code.github.io/

I've written up an explanation of what trips small models ups and how the harness can address that here https://yogthos.net/posts/2026-06-08-dirge-code.html

[−]Terretta · 2026-07-02 Thu 02:48 UTC · link
This really resonates. Thanks for mentioning.
[−]quantumleaper · 2026-07-02 Thu 03:27 UTC · link
Do you have benchmarks comparing against Pi? The blog post doesn't include any hard numbers.

For example, so far I haven't seen any evidence that LSP integration improves performance for small models vs using grep via a bash tool.

[−]polski-g · 2026-07-02 Thu 03:30 UTC · link
This is very impressive!
[−]vinceguidry · 2026-07-02 Thu 05:36 UTC · link
Very interesting work! I put some effort into getting it to work with models my hardware can actually run well and they just fall over immediately. gemma4 12b runs like molasses on my 2080 super but it was the only model able to, with your harness, actually do anything useful. It was the only useful thing I've gotten any model runnable with my hardware with any harness I've tried, very impressive!

I suspect smaller models need more work than is practical to fit harnesses around. The smaller the model, the more work, and it doesn't carry over to other small models.

Deepseek r1 7b could not emit tool calls to save its life, gemma4 e4b couldn't get the names of files right, qwen3.5 4b gets stuck in dumb rabbit holes, I pointed it at a ruby script and asked it to run it, it tried running it with bash then got caught in a loop investigating.

Noble effort though! I guess I'll keep working on my barebones ruby_llm harness, with very tempered expectations. Each of these failure modes can be worked around, but there's too many of them to work around in the general sense.