✳flâneur — a map of the web's best reading

[1906.01820] Risks from Learned Optimization in Advanced Machine Learning Systems

arxiv.org · 665 words · saved by 1 readers

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[1906.01820] Risks from Learned Optimization in Advanced Machine Learning Systems Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Artificial Intelligence arXiv:1906.01820 (cs) [Submitted on 5 Jun 2019 ( v1 ), last revised 1 Dec 2021 (this version, v3)] Title: Risks from Learned Optimization in Advanced Machine Learning Systems Authors: Evan Hubinger , Chris van Merwijk , Vladimir Mikulik , Joar Skalse , Scott Garrabrant View a PDF of the paper titled Risks from Learned Optimization

Explore this link on the map →

related reading