AI News

OpenAI Launches First Round of Embedded Assessments

Greg BrockmanUpdated Nov 17 01:15

AI summary

OpenAI announced a partnership with Apollo Research, METR_Evals, TransluceAI, and GoodfireAI to conduct embedded assessments, giving outside experts deep access to its internal models and systems to investigate alignment issues and test safety safeguards. Greg Brockman reposted the news, stating that the first round of assessments has begun.

Quoted post

OpenAI

@OpenAI

We’re working with @ApolloResearch, @METR_Evals, @TransluceAI, and @GoodfireAI on embedded assessments: giving outside experts deep access to our internal models and systems to investigate alignment and test our safeguards. These assessments build on our ongoing alignment and safety research, bringing independent scrutiny to how we identify and manage risks in our systems. https://t.co/SNAAG0uHmp

View original

We’re working with @ApolloResearch, @METR_Evals, @TransluceAI, and @GoodfireAI on embedded assessments: giving outside experts deep access to our internal models and systems to investigate alignment and test our safeguards. These assessments build on our ongoing alignment and safety research, bringing independent scrutiny to how we identify and manage risks in our systems. https://t.co/SNAAG0uHmp

View original post

Body

launching our first round of embedded assessments:

Source

Greg Brockman