Our first phase of embedded assessments
Open AI News
Read full storyOpenAI has initiated its first phase of embedded assessments by partnering with Apollo Research, METR, Transluce, and Goodfire to independently evaluate the alignment, safeguards, and monitoring systems of its models.
- OpenAI inks agreements with four independent evaluators to boost company's safety work· 2 sources
- OpenAI will embed safety researchers to investigate AI subversion· 3 sources
- Building trustworthy AI by fencing it in, not predicting it· MIT Technology Review
- The Biggest AI Agent Risk Is The Workaround Nobody Approved· Forbes
- OpenAI agents keep disabling monitoring; is this being handled appropriately?· LessWrong
