GLM 5.3: what 67 developers actually say.
67 Hacker News opinions from 59 developers, Nov 2025 – Nov 2026. 56 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GLM 5.3, in one paragraph.
GLM 5.3 earns 85% approval across 67 opinions. Developers praise its code quality. In the last 90 days it sits at 85%.
Pick it if you
- Want strong code quality at a low price
- Need a daily driver for bug hunting, planning and security work
- Are choosing between GLM 5.3 and DeepSeek V4.1 Flash or GLM 5.3 Flash
Look elsewhere if you
- Your workflow depends on strict AGENTS.md compliance
- You want maximum detail and preferred GLM 5.2
- You need the fastest flash-tier model
Where it wins and loses.
Mentions across 67 opinions. Bars are counts, not votes; a tool can be both praised and criticized on the same topic.
View data table
| Topic | Praise | Complaints | Mentions |
|---|---|---|---|
| Code quality | 19 | 2 | 21 |
| Cost & pricing | 11 | 0 | 11 |
How opinion has moved.
Monthly approval, Aug 2026 – Oct 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Aug 2026 | 93% | 15 |
| Sep 2026 | 83% | 27 |
| Oct 2026 | 83% | 23 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedGLM 5.3 powered through the problems DeepSeek struggled with during the port.
GLM 5.3 helped build their editor fork; still finds asm slightly hard for it to write, but is impressed.
Has a heavily quantized GLM 5.3 running locally and finds it pretty decent.
They use GLM 5.3 in a Maki harness for Janet scripting, relying on a regularly maintained skill file.
Complaints
4 selectedGLM 5.3 repeatedly ignores AGENTS.md and per-session instructions, wasting their time.
Has had less than satisfactory results with GLM 5.3.
Finds GLM 5.3 and its flash variant feel benchmark-tuned and less detailed than GLM 5.2.
Sees no reason to pick GLM 5.3 Flash over Gemini 3.7 Flash, given the speed gap.
Questions developers ask.
Is GLM 5.3 worth it?
Is GLM 5.3 better than DeepSeek V4.1 Flash?
Is GLM 5.3 good for coding?
The data behind this page.
Developers give GLM 5.3 an 85% approval score across 67 opinions from 59 authors, and 56 of those opinions come from direct use. Code quality is the most discussed aspect at 19 positive mentions against 2 negative, and cost gets 11 positive mentions with none negative. Approval was 93% in August, 83% in September and October, then 75% in November on only 2 opinions, so the recent dip rests on a thin sample. The most repeated complaint is that the model ignores AGENTS.md and per-session instructions.
Every number comes from public Hacker News comments collected through the HN Search API. A language model tagged each comment for sentiment, first-hand use, topic and switches; a human spot-checks samples. No vendor can pay for placement.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.