Concrete AI safety problems

OpenAI Blog ·

The landmark 'Concrete Problems in AI Safety' paper (Google Brain, OpenAI, Berkeley, Stanford) systematically enumerates research problems for ensuring ML systems behave as intended.

Categories: Research

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.