Cohere Blog company blog
Concerning behavior from a popular open-weight AI model
Discover how untrusted open-weight AI models can potentially leak data, even when self-hosted. Learn the security risks and how to protect your enterprise.
- Points
- 337
- HN comments
- 133
- Submissions
- 1
- Cited by
- 5 commenters
AI & Machine LearningSecurity & Privacy2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 26, 2026 | Concerning behavior from a popular open-weight AI model by matthieu_bl | 337 | 133 |
Cited in comments
Linked from 5 Hacker News comments by 5 different people, from Oct 2026 to Nov 2026.
Most recent:
- aftbit · Nov 6, 2026
- comboy · Nov 2, 2026
- rurban · Nov 1, 2026
- reilly3000 · Nov 1, 2026
- predkambrij · Oct 28, 2026
