P₂B: Plan to P₂B Better — AI Alignment Forum
tl;dr: Most good plans involve taking steps to make better plans. Making better plans is the convergent instrumental goal, of which all familiar convergent instrumental goals are an instance. This is key to understanding what agency is and why it is powerful. Planning means using a world model to predict the consequences of various courses of actions one could take, and taking actions that have good predicted consequences. (We think of this with the handle “doing things for reasons,” though we acknowledge this may be an idiosyncratic use of “reasons.”) We take “planning” to include things that are relevantly similar to this procedure, such as following a bag of heuristics that approximates it. We’re also including actually following the plans, in what might more clunkily be called “planning-acting.” Planning, in this broad sense, seems essential to the kind of goal-directed, consequential, agent-like intelligence that we expect to be highly impactful. This sequence explains why. Consid
x P₂B: Plan to P₂B Better — AI Alignment Forum Instrumental convergence Goal-Directedness Practical World Modeling AI Frontpage 28 P₂B: Plan to P₂B Better by Ramana Kumar , Daniel Kokotajlo 24th Oct 2021 7 min read 17 28 tl;dr: Most good plans involve taking steps to make better plans. Making better plans is the convergent instrumental goal, of which all familiar convergent instrumental goals are an instance. This is key to understanding what agency is and why it is powerful. Planning means using a world model to predict the consequences of various courses of actions one could take, and taking
Explore this link on the map →related reading
- Dive inmindingourway.com
- Instrumental convergence — LessWronglesswrong.com
- Instrumental convergence - Wikipediaen.wikipedia.org
- Agentshuyenchip.com
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- Why AIs aren't power-seeking yet — LessWronglesswrong.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- Plans A, B, C, and D for misalignment risk — LessWronglesswrong.com
- The Plan - 2023 Version — LessWronglesswrong.com
- Can we intentionally improve the world? Planners vs. Hayekians – Julia Galefjuliagalef.com