OpenAI News·· 3 d ago
Towards safety cases for frontier AI training
Towards safety cases for frontier AI training
AI summary
OpenAI published early guidance on safety cases for frontier AI training, covering technical safeguards, operational practices and investigation of misalignment incidents. It aims to provide a framework for arguing the safety of frontier-model training.
Selection record
Threshold 60Official, first-handFirst 42Second 31
Not admittedSum of both 73 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：标题正文均涉前沿AI训练安全
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: OpenAI News · openai.com