the QACI alignment plan: table of contents
post by Tamsin Leake (carado-1) · 2023-03-21T20:22:00.865Z · LW · GW · 1 commentsThis is a link post for https://carado.moe/qaci.html
Contents
1 comment
this post aims to keep track of posts relating to the question-answer counterfactual interval proposal for AI alignment [LW · GW], abbreviated "QACI" and pronounced "quashy". i'll keep it updated to reflect the state of the research.
this research is primarily published on the Orthogonal website and discussed on the Orthogonal discord.
as a top-level view of QACI, you might want to start with:
- an Evangelion dialogue explaining QACI [LW · GW]
- a narrative explanation of QACI [LW · GW]
- Orthogonal's Formal-Goal Alignment theory of change [LW · GW]
- formalizing the QACI formal-goal [LW · GW]
the set of all posts relevant to QACI includes:
- as overviews of QACI and how it's going:
- on the formal alignment perspective within which it fits:
- on the blob location problem:
- on QACI as an implementation of long reflection / CEV [? · GW]:
- on formalizing the QACI formal goal:
- a rough sketch of formal aligned AI using QACI [LW · GW] with some actual math
- one-shot AI, delegating embedded agency and decision theory, and one-shot QACI [LW · GW]
- on how a formally aligned AI would actually run over time:
- on the metaethics grounding QACI:
- on my view of the AI alignment research field within which i'm doing formal alignment:
1 comments
Comments sorted by top scores.
comment by Review Bot · 2024-05-02T21:48:30.992Z · LW(p) · GW(p)
The LessWrong Review [? · GW] runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year.
Hopefully, the review is better than karma at judging enduring value. If we have accurate prediction markets on the review results, maybe we can have better incentives on LessWrong today. Will this post make the top fifty?