OpenAI Blog company blog
Why language models hallucinate
OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and safety.
- Points
- 278
- HN comments
- 224
- Submissions
- 1
- Cited by
- 8 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 6, 2025 | Why language models hallucinate by simianwords | 278 | 224 |
Cited in comments
Linked from 8 Hacker News comments by 8 different people, from Sep 2025 to Dec 2025.
Most recent:
- bigfishrunning · Dec 18, 2025
- noboostforyou · Oct 14, 2025
- fragmede · Oct 14, 2025
- ACCount37 · Oct 13, 2025
- ricksunny · Sep 13, 2025
- gobdovan · Sep 10, 2025
