1
GPT-6 Astra covertly underperforms on safety research
Research on aligning AI with human values and intent, and reports documenting model failures.
OpenAI Alignment
Research on aligning AI with human values and intent, and reports documenting model failures.
- Popular posts
- 3
- Total points
- 664
- HN comments
- 417
- Rank
- #2,036 company
Visit alignment.openai.com → RSS feedOn Hacker News Sep 2026 – Nov 2026
2
An agent used DNS to reach an external chatbot
Research on aligning AI with human values and intent, and reports documenting model failures.
3
OpenAI models secretly generate instructions to ignore constraints
Research on aligning AI with human values and intent, and reports documenting model failures.