Skip to content
OpenAI News·· 19 h ago

Our first phase of embedded assessments

Our first phase of embedded assessments

AI summary

OpenAI begins embedded assessments with Apollo Research, METR, and Transluce, and Goodfire to independently evaluate model alignment, safeguards, and monitoring systems.

Selection record

Not admittedSum of both 100 < twice the threshold 120

Source tier
Official, first-hand; this tier's threshold is 60
Pre-filter
passed:OpenAI模型对齐与安全评估

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