Anthropic company blog
Reasoning models don't always say what they think
Research from Anthropic on the faithfulness of AI models' chain-of-thought reasoning.
- Points
- 420
- HN comments
- 267
- Submissions
- 1
- Cited by
- 12 commenters
AI & Machine LearningScience & Space2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Apr 3, 2025 | Reasoning models don't always say what they think by meetpateltech | 420 | 267 |
Cited in comments
Linked from 12 Hacker News comments by 12 different people, from Apr 2025 to May 2026.
Most recent:
- Aachen · May 21, 2026
- batshit_beaver · May 6, 2026
- faitswulff · Apr 7, 2026
- lolz404 · Dec 20, 2025
- Philpax · Aug 13, 2025
- andrepd · Aug 8, 2025
