{
localUrl: '../page/reflective_degree_of_freedom.html',
arbitalUrl: 'https://arbital.com/p/reflective_degree_of_freedom',
rawJsonUrl: '../raw/2fr.json',
likeableId: '1370',
likeableType: 'page',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
pageId: 'reflective_degree_of_freedom',
edit: '4',
editSummary: '',
prevEdit: '3',
currentEdit: '4',
wasPublished: 'true',
type: 'wiki',
title: 'Reflectively consistent degree of freedom',
clickbait: 'When an instrumentally efficient, self-modifying AI can be like X or like X' in such a way that X wants to be X and X' wants to be X', that's a reflectively consistent degree of freedom.',
textLength: '3798',
alias: 'reflective_degree_of_freedom',
externalUrl: '',
sortChildrenBy: 'likes',
hasVote: 'false',
voteType: '',
votesAnonymous: 'false',
editCreatorId: 'EliezerYudkowsky',
editCreatedAt: '2016-03-09 03:19:20',
pageCreatorId: 'EliezerYudkowsky',
pageCreatedAt: '2016-03-09 03:08:49',
seeDomainId: '0',
editDomainId: 'EliezerYudkowsky',
submitToDomainId: '0',
isAutosave: 'false',
isSnapshot: 'false',
isLiveEdit: 'true',
isMinorEdit: 'false',
indirectTeacher: 'false',
todoCount: '4',
isEditorComment: 'false',
isApprovedComment: 'true',
isResolved: 'false',
snapshotText: '',
anchorContext: '',
anchorText: '',
anchorOffset: '0',
mergedInto: '',
isDeleted: 'false',
viewCount: '184',
text: 'A "reflectively consistent degree of freedom" is when a self-modifying AI can have multiple possible properties $X_i \\in X$ such that an AI with property $X_1$ wants to go on being an AI with property $X_1,$ and an AI with $X_2$ will ceteris paribus only choose to self-modify into designs that are also $X_2,$ etcetera.\n\nThe archetypal reflectively consistent degree of freedom is a [humean_freedom Humean degree of freedom], the refective consistency of many different possible [1fw utility functions]. If Gandhi doesn't want to kill you, and you offer Gandhi a pill that makes him want to kill people, then [gandhi_stability_argument Gandhi will refuse the pill], because he knows that if he takes the pill then pill-taking-future-Gandhi will kill people, and the current Gandhi rates this outcome low in his preference function. Similarly, a [10h paperclip maximizer] wants to remain a paperclip maximizer. Since these two possible preference frameworks are both [71 consistent under reflection], they constitute a "reflectively consistent degree of freedom" or "reflective degree of freedom".\n\nFrom a design perspective, or the standpoint of an [1cv], the key fact about a reflectively consistent degree of freedom is that it doesn't automatically self-correct as a result of the AI trying to improve itself. The problem "Has trouble understanding General Relativity" or "Cannot beat a human at poker" or "Crashes on seeing a picture of a dolphin" is something that you might expect to correct automatically and without specifically directed effort, assuming you otherwise improved the AI's general ability to understand the world and that it was self-improving. "Wants paperclips instead of eudaimonia" is *not* self-correcting.\n\nAnother way of looking at it is that reflective degrees of freedom describe information that is not automatically extracted or learned given a sufficiently smart AI, the way it would automatically learn General Relativity. If you have a concept whose borders (membership condition) relies on knowing about General Relativity, then when the AI is sufficiently smart it will see a simple definition of that concept. If the concept's borders instead rely on [ value-laden] judgments, there may be no algorithmically simple description of that concept, even given lots of knowledge of the environment, because the [humean_freedom Humean degrees of freedom] need to be independently specified.\n\nOther properties besides the preference function look like they should be reflectively consistent in similar ways. For example, [ son of CDT] and [ UDT] both seem to be reflectively consistent in different ways. So an AI that has, from our perspective, a 'bad' decision theory (one that leads to behaviors we don't want), isn't 'bugged' in a way we can rely on to self-correct. (This is one reason why MIRI studies decision theory and not computer vision. There's a sense in which mistakes in computer vision automatically fix themselves, given a sufficiently advanced AI, and mistakes in decision theory don't fix themselves.)\n\nSimilarly, [27p Bayesian priors] are by default consistent under reflection - if you're a Bayesian with a prior, you want to create copies of yourself that have the same prior or [1ly Bayes-updated] versions of the prior. So 'bugs' (from a human standpoint) like being [Pascal's Muggable](https://wiki.lesswrong.com/wiki/Pascal's_mugging) might not automatically fix themselves in a way that correlated with sufficient growth in other knowledge and general capability, in the way we might expect a specific mistaken belief about gravity to correct itself in a way that correlated to sufficient general growth in capability. (This is why MIRI thinks about [ naturalistic induction] and similar questions about prior probabilities.)',
metaText: '',
isTextLoaded: 'true',
isSubscribedToDiscussion: 'false',
isSubscribedToUser: 'false',
isSubscribedAsMaintainer: 'false',
discussionSubscriberCount: '1',
maintainerCount: '1',
userSubscriberCount: '0',
lastVisit: '',
hasDraft: 'false',
votes: [],
voteSummary: 'null',
muVoteSummary: '0',
voteScaling: '0',
currentUserVote: '-2',
voteCount: '0',
lockedVoteType: '',
maxEditEver: '0',
redLinkCount: '0',
lockedBy: '',
lockedUntil: '',
nextPageId: '',
prevPageId: '',
usedAsMastery: 'false',
proposalEditNum: '0',
permissions: {
edit: {
has: 'false',
reason: 'You don't have domain permission to edit this page'
},
proposeEdit: {
has: 'true',
reason: ''
},
delete: {
has: 'false',
reason: 'You don't have domain permission to delete this page'
},
comment: {
has: 'false',
reason: 'You can't comment in this domain because you are not a member'
},
proposeComment: {
has: 'true',
reason: ''
}
},
summaries: {},
creatorIds: [
'EliezerYudkowsky'
],
childIds: [
'humean_free_boundary',
'value_laden'
],
parentIds: [
'reflective_stability'
],
commentIds: [
'2gh'
],
questionIds: [],
tagIds: [],
relatedIds: [],
markIds: [],
explanations: [],
learnMore: [],
requirements: [],
subjects: [],
lenses: [],
lensParentId: '',
pathPages: [],
learnMoreTaughtMap: {},
learnMoreCoveredMap: {},
learnMoreRequiredMap: {},
editHistory: {},
domainSubmissions: {},
answers: [],
answerCount: '0',
commentCount: '0',
newCommentCount: '0',
linkedMarkCount: '0',
changeLogs: [
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8423',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '4',
type: 'newChild',
createdAt: '2016-03-09 03:22:08',
auxPageId: 'humean_free_boundary',
oldSettingsValue: '',
newSettingsValue: ''
},
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8422',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '4',
type: 'newEdit',
createdAt: '2016-03-09 03:19:20',
auxPageId: '',
oldSettingsValue: '',
newSettingsValue: ''
},
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8419',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '3',
type: 'newEdit',
createdAt: '2016-03-09 03:11:53',
auxPageId: '',
oldSettingsValue: '',
newSettingsValue: ''
},
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8418',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '2',
type: 'newEdit',
createdAt: '2016-03-09 03:11:14',
auxPageId: '',
oldSettingsValue: '',
newSettingsValue: ''
},
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8417',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '1',
type: 'newEdit',
createdAt: '2016-03-09 03:08:49',
auxPageId: '',
oldSettingsValue: '',
newSettingsValue: ''
},
{
likeableId: '0',
likeableType: 'changeLog',
myLikeValue: '0',
likeCount: '0',
dislikeCount: '0',
likeScore: '0',
individualLikes: [],
id: '8416',
pageId: 'reflective_degree_of_freedom',
userId: 'EliezerYudkowsky',
edit: '0',
type: 'newParent',
createdAt: '2016-03-09 02:39:44',
auxPageId: 'reflective_stability',
oldSettingsValue: '',
newSettingsValue: ''
}
],
feedSubmissions: [],
searchStrings: {},
hasChildren: 'true',
hasParents: 'true',
redAliases: {},
improvementTagIds: [],
nonMetaTagIds: [],
todos: [],
slowDownMap: 'null',
speedUpMap: 'null',
arcPageIds: 'null',
contentRequests: {}
}