Anthropic company blog
Alignment faking in large language models
A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models
- Points
- 302
- HN comments
- 353
- Submissions
- 1
- Cited by
- 7 commenters
AI & Machine LearningSecurity & Privacy2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Dec 19, 2024 | Alignment faking in large language models by adultorata | 302 | 353 |
Cited in comments
Linked from 7 Hacker News comments by 7 different people, from Dec 2024 to Jul 2026.
Most recent:
- sailingparrot · Jul 24, 2026
- theptip · Jun 19, 2026
- spkavanagh6 · Feb 21, 2026
- rybosworld · Feb 21, 2026
- GavCo · Dec 9, 2025
- anon373839 · Apr 3, 2025
