Concrete Problems in AI Safety, Revisited
It addresses the problem of AI safety failures for the AI community, but is incremental in proposing a refined framing rather than new solutions.
The paper analyzes real-world incidents to show that current AI safety vocabulary is insufficient, advocating for an expanded socio-technical framing to better understand failures and successes in AI deployment.
As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real life.