Gemini 3: what 70 developers actually say.
70 Hacker News opinions from 67 developers, Nov 2025 – Nov 2026. 58 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
The case for Gemini 3, in one paragraph.
Gemini 3 earns 56% approval across 70 opinions. Developers praise its code quality.
Pick it if you
- Want fast UI and app scaffolding from short prompts
- Need to pull data from PDFs, drawings or scans
- Have short, clear tasks and will review the output
Look elsewhere if you
- Need dependable long-running agent sessions
- Rely on stable GitHub Copilot integration
- Need strong multi-step reasoning or loop-free tool calls
Where it wins and loses.
Mentions across 70 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 | 15 | 9 | 24 |
| Reliability | 2 | 9 | 11 |
How opinion has moved.
Monthly approval, Nov 2025 – Feb 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Nov 2025 | 64% | 22 |
| Dec 2025 | 50% | 17 |
| Jan 2026 | 60% | 15 |
| Feb 2026 | 59% | 11 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedGemini 3 greatly helped build a Redis-compatible cache, including reasoning through Raft edge cases and generating tests.
Recent models including Gemini 3 now handle complex compiler and hardware tasks.
Vibe coded a retro emulator and assembler with Gemini 3 using minimal prompts, with great results.
Switched to Gemini 3 and found the agent much smoother than with Kimi 2.5.
Complaints
4 selectedGemini 3.x hung, looped, and hallucinated on longer tasks, making it unusable for serious work.
Gemini 3 kept sending them from one post-mortem report to another.
Reports Gemini 3 was unreliable in GitHub Copilot with frequent server errors, and unusable for two months.
Finds Gemini 3 useless and says it hallucinates more than Gemini 2.5.
Questions developers ask.
Is Gemini 3 worth it?
Is Gemini 3 better than Claude Opus 4.5?
Is Gemini 3 reliable for coding?
The data behind this page.
Developers are split on Gemini 3 for software work. Approval is 56% across 70 opinions from 67 authors, and 58 of those opinions come from firsthand use. Code quality mentions lean positive at 15 to 9, while reliability is negative at 2 to 9. Volume fell from 22 opinions in November 2025 to 1 or 2 opinions in each month with data since March 2026, and the recent 0%, 0%, 100% and 25% readings rest on one or two 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.