GPT-5.5: what 236 developers actually say.
236 Hacker News opinions from 221 developers, Nov 2025 – Nov 2026. 203 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for GPT-5.5, in one paragraph.
GPT-5.5 earns 69% approval across 236 opinions. Developers praise its code quality. In the last 90 days it sits at 67%.
Pick it if you
- Want high code quality marks (91 positive mentions to 23 negative)
- Care about speed (13 positive to 1 negative)
- Already work in Codex or Copilot and want a cheaper option
Look elsewhere if you
- Need steady reliability across long sessions (17 positive to 15 negative)
- Depend on context compaction to keep a plan on track
- Need clean edits without extra indirection or missed formatting steps
Where it wins and loses.
Mentions across 236 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 | 91 | 23 | 114 |
| Speed | 13 | 1 | 14 |
| Autonomy | 9 | 6 | 15 |
| Reliability | 17 | 15 | 32 |
| Cost & pricing | 10 | 8 | 18 |
How opinion has moved.
Monthly approval, Apr 2026 – Sep 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Apr 2026 | 78% | 18 |
| May 2026 | 73% | 71 |
| Jun 2026 | 74% | 71 |
| Jul 2026 | 57% | 53 |
| Aug 2026 | 90% | 10 |
| Sep 2026 | 33% | 9 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedUses GPT-5.5 in Copilot for heavy Visual Studio work, calling it more than sufficient for under $100/month.
Finds GPT-5.5 medium much better for embedded Lisp and C, with clearer, more direct output.
GPT-5.5 is still their main driver for coding work.
Finds GPT-5.5 models more than enough for most programming tasks.
Complaints
4 selectedGPT-5.5 struggled with standard GHC Haskell, needing more turns than for Java or TypeScript.
GPT-5.5 compaction had major issues and its reasoning output became less coherent.
GPT-5.5 did not stay on track after context compaction.
GPT-5.5 was bad, and usage resets and bugs made them stop paying $200/mo.
Questions developers ask.
Is GPT-5.5 worth it?
Is GPT-5.5 better than Claude Opus 4.8?
Why do developers stop using GPT-5.5?
The data behind this page.
Developers give GPT-5.5 69% approval across 236 opinions from 221 authors, and 203 of those opinions come from firsthand use. Code quality drives the score with 91 positive mentions against 23 negative, and speed is the cleanest signal at 13 to 1. Reliability is close to even at 17 positive and 15 negative, and long sessions after context compaction draw repeated complaints. Approval held at 73 to 74 in May and June, fell to 57 in July, and sits at 67 over the last 90 days on thin recent volume.
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.