Concepedia

Joar Skalse

JS

4

Publications

66

Citations

4

H-Index

2019

Active since

Affiliations

University of Oxford(Current)

Joar Skalse is an author at University of Oxford specializing in computer science, data science, and engineering.

Top concepts

Publications per year

2019–2024

4

Publications

4

Risks from Learned Optimization in Advanced Machine Learning Systems

Evan Hubinger, Chris van Merwijk, Vladimir Mikulik et al. · arXiv (Cornell University) · 2019 · 25 citations · Full text

, , +12

Defining and Characterizing Reward Hacking

Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov et al. · arXiv (Cornell University) · 2022 · 18 citations · Full text

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

David Dalrymple, Joar Skalse, Yoshua Bengio et al. · arXiv (Cornell University) · 2024 · 12 citations · Full text

Neural networks are a priori biased towards Boolean functions with low entropy

Chris Mingard, Joar Skalse, Guillermo Valle-Pérez et al. · arXiv (Cornell University) · 2019 · 11 citations · Full text

Rows per page

1–4 of 4