OpenAI Blog · Jun 21, 2016
Concrete AI safety problems
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Concrete AI safety problems. 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. The paper explores many research problems around ensuring that modern machine learning systems operate as intended. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Concrete AI safety problems' affects your current setup before relying on it in production.
ai