GPT-5.3 Codex: what 54 developers actually say.
54 Hacker News opinions from 51 developers, Nov 2025 – Nov 2026. 51 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GPT-5.3 Codex, in one paragraph.
GPT-5.3 Codex earns 74% approval across 54 opinions. Developers praise its code quality.
Pick it if you
- Work on backend and systems tasks
- Need a low-cost daily driver for scripting and greenfield work
- Care most about price for everyday coding
Look elsewhere if you
- Work mainly in R
- Need dependable long autonomous runs
- Need strict test coverage and clean refactors
Where it wins and loses.
Mentions across 54 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 | 16 | 7 | 23 |
| Cost & pricing | 9 | 1 | 10 |
How opinion has moved.
Monthly approval, Feb 2026 – Jun 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Feb 2026 | 79% | 19 |
| Mar 2026 | 57% | 15 |
| Apr 2026 | 72% | 9 |
| Jun 2026 | 80% | 5 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedConsiders GPT-5.3 Codex the peak of coding models and misses it for writing good code without overstepping.
GPT-5.3-Codex was excellent for backend and systems tasks.
GPT-5.3 Codex balances quality and cost well, cheap enough to use on almost everything.
Calls GPT-5.3 Codex possibly OpenAI's best coding model, about 90% of GPT-5.5 at a fraction of the cost.
Complaints
4 selectedHad poor results with GPT-5.3 Codex, so used GPT-5.2 for design and 5.3 Codex only for execution.
GPT-5.3-Codex falls short on R programming work.
Started quickly but got stuck in a five-hour loop that made no further progress on the clone task.
Describes Codex 5.3 injecting a CSS hack instead of properly refactoring the markup.
Questions developers ask.
Is GPT-5.3 Codex worth it?
Is GPT-5.3 Codex better than Claude Opus 4.6?
Is GPT-5.3 Codex reliable?
The data behind this page.
GPT-5.3 Codex has 74% approval across 54 opinions from 51 authors. Developers praise its code quality (16 positive, 7 negative) and cost (9 positive, 1 negative), and several prefer it to Claude Opus 4.6 or GPT-5.5. Reliability is the weak spot at 3 positive and 4 negative, with reports of long loops and weak tests. Approval was 57% in March 2026, then 72% to 100% in the April to September entries, which have only 2 to 9 opinions each.
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.