GPT-5.4: what 114 developers actually say.
114 Hacker News opinions from 105 developers, Nov 2025 – Nov 2026. 101 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GPT-5.4, in one paragraph.
GPT-5.4 earns 72% approval across 114 opinions. Developers praise its code quality.
Pick it if you
- Want strong code quality on large repositories
- Need steady task adherence through long context compactions
- Care about price at high usage volume
Look elsewhere if you
- Need reliable orchestration of large multi-file workflows
- Want security analysis on your own repositories
- Expect accurate bug detection during code review
Where it wins and loses.
Mentions across 114 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 | 37 | 14 | 51 |
| Cost & pricing | 12 | 2 | 14 |
| Reliability | 10 | 7 | 17 |
How opinion has moved.
Monthly approval, Mar 2026 – Sep 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Mar 2026 | 61% | 23 |
| Apr 2026 | 75% | 61 |
| May 2026 | 44% | 9 |
| Jun 2026 | 91% | 11 |
| Jul 2026 | 60% | 5 |
| Sep 2026 | 100% | 4 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedGPT-5.4 hits a sweet spot at work: usually right, and easy to supervise and correct.
Calls GPT-5.4 the best model they've tested for task adherence, even over multiple compactions.
GPT-5.4 is the only model that behaved well across context compactions on a large task.
GPT-5.4 would prefer using LSP renaming tools as instructed.
Complaints
4 selectedGPT-5.4 started refusing to examine potential security problems in their repos.
Feels GPT-5.4 has gotten worse than it used to be.
GPT 5.4 failed a complicated coding problem that Kimi 2.7 solved.
They were really frustrated with GPT-5.4 before their later Codex session went well.
Questions developers ask.
Is GPT-5.4 worth it?
Is GPT-5.4 better than Claude Opus 4.6?
Is GPT-5.4 good for large codebases?
The data behind this page.
GPT-5.4 holds 72% approval across 114 opinions from 105 authors, and code quality is the clearest strength at 37 positive mentions against 14 negative. Developers praise its task adherence, context compaction and price, with cost drawing 12 positive mentions and 2 negative, and 6 positive mentions on large codebases with no complaints. The trend is uneven: April 2026 carried most of the data at 61 opinions and 75% approval, while June through September total 21 opinions at 91% to 100% approval, so the recent rise rests on thin samples. Complaints focus on forgotten instructions, missed bugs in review, wasted effort checking diffs and weak orchestration of large workflows.
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.