The ‘ awful idea of accountability ’ : inscribing people into the measurement of objects

By K. Hoskin, Vos. 2021

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. J'er'emy Scheurer
2. Anca Dragan
3. Stephen Casper
4. Tomasz Korbak
5. Xander Davies
6. Dylan Hadfield-Menell
7. Dorsa Sadigh
8. David Krueger

Citations in the corpus

• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (2023, background): “Applying strong optimization pressure for an imperfect proxy measure for a goal tends to cause poor performance on the underlying target goal [Hoskin, 1996, Manheim and Garrabrant, 2018, Gao et al., 2022].”