Research on aligning AI with human values and intent, and reports documenting model failures.
0 comments
No comments yet.
Related stories
- OpenAI: Self-replicating prompt injections existalignment.openai.comHacker News · 1 points · 4 days ago
- DEV Community · 3 points · 4 days ago
- Self-generated prompt injections in compaction summariessimonwillison.netHacker News · 1 points · 10 days ago
- Hacker News · 2 points · 1 day ago
- Show HN: Air-gapped file encryption as self-decrypting HTML pagecms-sfx-demo.apeleg.comHacker News · 90 points · 7 days ago
- Hacker News · 2 points · 10 days ago