Concrete AI safety problems
The landmark 'Concrete Problems in AI Safety' paper (Google Brain, OpenAI, Berkeley, Stanford) systematically enumerates research problems for ensuring ML systems behave as intended.
Excerpt
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.
Read at source: https://openai.com/index/concrete-ai-safety-problems