Doug Turnbull personal blog
Don't classify, hallucinate
A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.
- Points
- 246
- HN comments
- 107
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSoftware Engineering2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Aug 10, 2026 | Don't classify, hallucinate by softwaredoug | 246 | 107 |
