Anthropic company blog
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
- Points
- 1,072
- HN comments
- 394
- Submissions
- 1
- Cited by
- 43 commenters
AI & Machine LearningSoftware Engineering2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Mar 27, 2025 | Tracing the thoughts of a large language model by Philpax | 1,072 | 394 |
Cited in comments
Linked from 48 Hacker News comments by 43 different people, from Mar 2025 to Sep 2026.
Most recent:
- tomrod · Sep 30, 2026
- libraryofbabel · Aug 24, 2026
- fwip · Aug 24, 2026
- steveklabnik · Jul 6, 2026
- mdp2021 · Jun 25, 2026
- kgeist · Jun 8, 2026
