Key Components of an RSP - ARC Evals
This document lists the key components of responsible scaling policy, with rough sample language for each: Limits, Protections, Evaluations, Response, and Accountability.
Key Components of an RSP - METR Our Work Research Notes Updates Risk Assessment About Donate Careers Search --> Our Work Research Notes Updates Risk Assessment About Donate Careers Menu × Key Components of an RSP CONTRIBUTORS Beth Barnes DATE September 26, 2023 SHARE Copy Link Citation BibTeX Citation × @misc { metr-2023-rsp-key-components , title = {Key Components of an RSP} , author = {Beth Barnes} , howpublished = {\url{https://metr.org/rsp-key-components/}} , year = {2023} , month = {09} , } Copy This document lists some key components of a responsible scaling policy, with roug
Explore this link on the map →related reading
- Responsible Scaling Policy v3 — LessWronglesswrong.com
- Responsible Scaling Policies (RSPs) - METRevals.alignment.org
- Responsible Scaling Policies (RSPs) - METRmetr.org
- 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
- Thoughts on responsible scaling policies and regulation — LessWronglesswrong.com
- Anthropic's Responsible Scaling Policy \ Anthropicanthropic.com
- Responsible Scaling Policy Updates \ Anthropicanthropic.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- How Can AI Labs Incorporate Risks From AI Accelerating AI Progress Into Their Responsible Scaling Policies?forethought.org
- Three Sketches of ASL-4 Safety Case Componentsalignment.anthropic.com