GPT-5.2: what developers actually say
We read every Hacker News comment from Nov 2025 – Nov 2026 that gave a real opinion on GPT-5.2. 73 of the 82 opinions come from people who say they use it themselves.
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.
Pick it if
- 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
- Need strict instruction following
- Depend on reliable tool calling
- Need low cost and few rollbacks
Strengths and weaknesses
Each row counts opinions that mentioned the topic. Bars to the right of the line are praise, bars to the left are complaints.
How opinion has moved
What developers say
Praise
Complaints
Summaries are paraphrased. Each links to the original comment.
GPT-5.2 compared
FAQ
Is GPT-5.2 worth it?
It has 68% approval across 82 opinions. Code quality is positive at 28 to 12, while reliability is split 8 to 8.
Is GPT-5.2 better than Claude Opus 4.5?
Seven people preferred GPT-5.2 over Claude Opus 4.5, and three preferred Opus 4.5. These are Hacker News opinion counts.
Is GPT-5.2 reliable?
Reliability mentions are split 8 positive and 8 negative. Some users report lost context and tool calls that need tuned reasoning to work.