Oxford and Top AI Labs Propose Positive Alignment
Sixteen researchers from Oxford, Google DeepMind, OpenAI and Anthropic published a paper on "Positive Alignment," arguing that safe AI is not necessarily good AI and that even a 97% interception rate is insufficient.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Oxford, DeepMind, OpenAI & Anthropic paper argues safe AI isn't the same as good AI — alex_verem · 2026-11-17
- 16 researchers from Oxford, DeepMind, OpenAI, Anthropic: safe AI isn't the same as good AI — alex_verem · 2026-11-17