Responsible Scaling Policies (RSPs) - ARC Evals
We describe the basic components of Responsible Scaling Policies (RSPs) as well as why we find them promising for reducing catastrophic risks from AI.
Responsible Scaling Policies (RSPs) - METR Our Work Research Notes Updates Risk Assessment About Donate Careers Language English Español 中文 Search --> Our Work Research Notes Updates Risk Assessment About Donate Careers English Español 中文 English Español 中文 Menu × Responsible Scaling Policies (RSPs) CONTRIBUTORS Beth Barnes , Hjalmar Wijk , and Lawrence Chan DATE September 26, 2023 SHARE Copy Link Citation BibTeX Citation × @misc { metr-2023-rsp , title = {Responsible Scaling Policies (RSPs)} , author = {Beth Barnes, Hjalmar Wijk, Lawrence Chan} , howpublished = {\url{https://metr.
Explore this link on the map →related reading
- Responsible Scaling Policies (RSPs) - METRmetr.org
- Responsible Scaling Policy v3 — LessWronglesswrong.com
- Key Components of an RSP - METRevals.alignment.org
- Thoughts on responsible scaling policies and regulation — LessWronglesswrong.com
- Responsible Scaling Policy Version 3.0 \ Anthropicanthropic.com
- RSPs are pauses done right — EA Forumforum.effectivealtruism.org
- Dario Amodei’s prepared remarks from the AI Safety Summit on Anthropic’s Responsible Scaling Policy \ Anthropicanthropic.com
- Anthropic's Responsible Scaling Policy \ Anthropicanthropic.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- How Can AI Labs Incorporate Risks From AI Accelerating AI Progress Into Their Responsible Scaling Policies?forethought.org
- Responsible Scaling Policy Updates \ Anthropicanthropic.com
- Dario Amodei — Policy on the AI Exponentialdarioamodei.com