The paper presents five practical research problems related to accident risk in machine learning systems, grouped by whether they originate from a wrong objective function, an objective function too expensive to evaluate frequently, or undesirable behaviour during learning.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Concrete Problems in AI Safety → states its contribution → The paper presents five practical research problems related to accident risk in machine learning systems, grouped by whether they originate from a wrong objective function, an objective function too expensive to evaluate frequently, or undesirable behaviour during learning.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.