Interpretability — LessWrong
Chris Olah wrote the following topic prompt for the Open Phil 2021 request for proposals on the alignment of AI systems. We (Asya Bergal and Nick Bec…
x Interpretability — LessWrong Open Philanthropy 2021 AI Alignment RFP Interpretability (ML & AI) AI Frontpage 61 Interpretability by abergal , Nick_Beckstead 29th Oct 2021 AI Alignment Forum 14 min read 13 61 Ω 33 Chris Olah wrote the following topic prompt for the Open Phil 2021 request for proposals on the alignment of AI systems. We (Asya Bergal and Nick Beckstead) are running the Open Phil RFP and are posting each section as a sequence on the Alignment Forum. Although Chris wrote this document, we didn’t want to commit him to being responsible for responding to comments on it by posting i
related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- On Optimism for Interpretabilitygoodfire.ai
- An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
- Assessing skeptical views of interpretability research | Christopher Pottsweb.stanford.edu
- A Pragmatic Vision for Interpretability — LessWronglesswrong.com
- The Building Blocks of Interpretabilitydistill.pub
- What is the purpose of interpretability?ericjmichaud.com
- Softmax Linear Unitstransformer-circuits.pub
- How Can Interpretability Researchers Help AGI Go Well? — AI Alignment Forumalignmentforum.org
- How To Go From Interpretability To Alignment: Just Retarget The Search — LessWronglesswrong.com
- Chris Olah’s views on AGI safety — LessWronglesswrong.com