OpenAI News·· 15 h ago
Securing our frontier model training environment
Securing our frontier model training environment
AI summary
OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.
Selection record
Threshold 60Official, first-handFirst 42Second 58
Not admittedSum of both 100 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：OpenAI前沿模型训练安全与红队评测
- Same event
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