Cosma Shalizi personal blog
"Attention", "Transformers", in Neural Network "Large Language Models"
I find this literature irritating and opaque. This is at least somewhat because I do not yet understand it well, and there's too much of it. But clearly I need to wrap my head around it, before I become technically obsolete. My scare quotes in the title of these notes thus derive in part from jealousy and fear. But…
- Points
- 300
- HN comments
- 76
- Submissions
- 1
- Cited by
- 17 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Dec 24, 2023 | "Attention", "Transformers", in Neural Network "Large Language Models" by macleginn | 300 | 76 |
Cited in comments
Linked from 19 Hacker News comments by 17 different people, from May 2023 to Jul 2026.
Most recent:
- thaumasiotes · Jul 29, 2026
- hnsr · Jun 6, 2026
- v9v · Jun 5, 2026
- omnicognate · Jan 20, 2026
- mbeex · Jan 8, 2026
- roadside_picnic · Dec 22, 2025
