Concrete AI safety problems

OpenAI

We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety⁠(opens in a new window). The paper explores many research problems around ensuring that modern machine learning systems operate as intended.

The authors discuss five areas:

Many of the problems are not new, but the paper explores them in the context of cutting-edge systems. We hope they’ll inspire more people to work on AI safety research, whether at OpenAI⁠ or elsewhere.

We’re particularly excited to have participated in this paper as a cross-institutional collaboration. We think that broad AI safety collaborations will enable everyone to build better machine learning systems. Let us know⁠(opens in a new window) if you have a future paper you’d like to collaborate on!