GPT-5: what 62 developers actually say.
62 Hacker News opinions from 58 developers, Nov 2025 – Nov 2026. 54 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GPT-5, in one paragraph.
GPT-5 earns 57% approval across 62 opinions. Developers are divided on it, while code quality is the recurring complaint.
Pick it if you
- Want dependable JSON output under strict constraints
- Want an agent that explores codebases through git
- Value reliable tool use with some autonomy
Look elsewhere if you
- Need consistent design intent on large projects
- Work mainly in Lisp or niche languages
- Need long context and stable behavior over many turns
Where it wins and loses.
Mentions across 62 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 |
|---|---|---|---|
| Reliability | 8 | 5 | 13 |
| Code quality | 13 | 14 | 27 |
How opinion has moved.
Monthly approval, Nov 2025 – Jul 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Nov 2025 | 52% | 24 |
| Dec 2025 | 94% | 8 |
| Jan 2026 | 69% | 8 |
| May 2026 | 40% | 5 |
| Jul 2026 | 20% | 5 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedThe original GPT-5 adhered closely to prompts, which they praise.
GPT-5 and its early post-trained releases were excellent at following task instructions.
Reports GPT-5 and later never erred filling structured JSON under many constraints across hundreds of runs.
Mid-tier GPT-5 is about as competitive as Sonnet for their workflow.
Complaints
4 selectedGPT-5 kept running wrong uv commands or using pip despite AGENTS.md instructions.
GPT-5 handled R coding terribly a year ago, which led them to switch to Gemini.
Found early GPT-5 added flashy, overwrought frontend styling and needed heavy prompting to stop it.
Finds GPT-5 models nitpicky and over-defensive in code, though useful for review and math.
Questions developers ask.
Is GPT-5 worth it for coding?
Is GPT-5 better than Claude Sonnet 4.5?
What are GPT-5's main weaknesses?
The data behind this page.
GPT-5 has 57% approval across 62 opinions from 58 authors; 54 opinions are firsthand. Code quality is the main point of disagreement at 13 positive and 14 negative, while reliability is 8 positive to 5 negative and autonomy is 3 to 0. Recent monthly approval is volatile and based on small samples: 20% in July, 0% in August, 50% in September and 100% in October, on 1 to 5 opinions per month. Those recent samples are too small to show a stable direction.
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.