RSPs are pauses done right — EA Forum
COI: I am a research scientist at Anthropic, where I work on model organisms of misalignment; I was also involved in the drafting process for Anthrop…
RSPs are pauses done right — EA Forum Hide table of contents RSPs are pauses done right by evhub Oct 14 2023 8 min read 6 93 AI safety AI moratorium Frontpage RSPs are pauses done right How do we make it to a state where AI goes well? Reasons to like RSPs How do RSPs relate to pauses and pause advocacy? 6 comments COI: I am a research scientist at Anthropic, where I work on model organisms of misalignment ; I was also involved in the drafting process for Anthropic’s RSP . Prior to joining Anthropic, I was a Research Fellow at MIRI for three years. Thanks to Kate Woolverton, Carson Denison, and
Explore this link on the map →saved by
related reading
- Responsible Scaling Policy v3 — LessWronglesswrong.com
- Responsible Scaling Policy Version 3.0 \ Anthropicanthropic.com
- Responsible Scaling Policies (RSPs) - METRevals.alignment.org
- Thoughts on responsible scaling policies and regulation — LessWronglesswrong.com
- Responsible Scaling Policies (RSPs) - METRmetr.org
- Key Components of an RSP - METRevals.alignment.org
- Policy ideas for mitigating AI risk — EA Forumforum.effectivealtruism.org
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- 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
- Comments on Manheim's "What's in a Pause?" — EA Forumforum.effectivealtruism.org
- AI Pause Will Likely Backfire — EA Forumforum.effectivealtruism.org