GPT-5.2: what 82 developers actually say.
82 Hacker News opinions from 77 developers, Nov 2025 – Nov 2026. 73 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GPT-5.2, in one paragraph.
GPT-5.2 earns 68% approval across 82 opinions. Developers praise its code quality.
Pick it if you
- Want strong code quality, at 28 positive to 12 negative mentions
- Need a reviewer for code written by Claude Code
- Want more usage per $20 subscription than Claude
Look elsewhere if you
- Need strict instruction following
- Depend on reliable tool calling
- Need low cost and few rollbacks
Where it wins and loses.
Mentions across 82 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 | 28 | 12 | 40 |
| Reliability | 8 | 8 | 16 |
How opinion has moved.
Monthly approval, Dec 2025 – Apr 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Dec 2025 | 71% | 26 |
| Jan 2026 | 79% | 21 |
| Feb 2026 | 63% | 26 |
| Mar 2026 | 33% | 3 |
| Apr 2026 | 50% | 4 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedRemembers GPT-5.2 Codex performing fine.
The release of GPT-5.2 was a major boost to their productivity.
Finds GPT-5.2 and later models generally better coders than Opus 4.6.
GPT-5.2 or 5.3 works very well as a reviewer of code written by Claude Code.
Complaints
4 selectedAfter three months of pair programming, judged Codex 5.2 significantly worse than Claude Sonnet on cost and rollbacks.
Could not get GPT-5.2 to follow instructions, even with repeated prompts.
GPT-5.2 in OpenCode misses what they're doing, loses context, and was very slow on a refactor.
GPT-5.2 needed tuned reasoning to make tool calling reliable and trails Claude.
Questions developers ask.
Is GPT-5.2 worth it?
Is GPT-5.2 better than Claude Opus 4.5?
Is GPT-5.2 reliable?
The data behind this page.
Developers give GPT-5.2 68% approval across 82 opinions from 77 authors, and 73 are firsthand. Code quality drives the positive view, at 28 positive mentions against 12 negative, and users also praise it as a reviewer of Claude Code output and for usage per $20. Approval rose from 71% in December to 79% in January, then fell to 63% in February; later samples hold only 1 to 4 opinions, so the recent trend is thin. Reliability is the main concern, at 8 positive and 8 negative mentions, with complaints about lost context, weak instruction following, and unreliable tool calls.
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.