Why hackers moved from OpenAI models to Claude
1 hacker described this switch in public comments. Their words, with links to the originals.
What hackers said about the move
“I switched from OpenAI models to using Anthropic ones some time ago”BugsJustFindMe, 2025-12-26original comment ↗
Use OpenAI models? Get alerted when hackers criticize it.
Tell us the tools in your stack. When hackers start criticizing one of them, or moving to an alternative, you will hear about it first.
OpenAI models vs Claude
| OpenAI models | Claude | |
|---|---|---|
| Hackers who recommend | 0 | 24 |
| Hackers who criticize | 2 | 25 |
| Moved away from it | 1 | 13 |
| Moved to it | 0 | 11 |
Counts are distinct hackers in the sampled comments, not market share.
Criticism of OpenAI models
“I see this behavior for both OpenAI and Anthropic models (for several harnesses as well).”asabla, 2026-09-28original comment ↗
Praise for Claude
“those apps while not the best gui apps, already infinitely better than tui”nsonha, 2026-10-01original comment ↗
“I recently switched from Codex to Claude”RestartKernel, 2026-09-16original comment ↗
“I absolutely love Claude's coding capabilities”pid0x17, 2026-09-15original comment ↗
“claude was able to diagnose that the 2013 rail is around 11.44v (outside of the 10v range iirc)”jlawrence6809, 2026-09-02original comment ↗
“So far all the suggestion that Opus 5.0 offered me, always aligned with what i wanted.”benjiro29, 2026-08-13original comment ↗