LESSWRONGTags
LW

Deconfusion

EditHistory
Discussion (0)
Help improve this page (3 flags)
EditHistory
Discussion (0)
Help improve this page (3 flags)
Deconfusion
Random Tag
Contributors
2abramdemski

Narrowly, deconfusion is a specific branch of AI alignment research, discussed in MIRI's 2018 research update. More broadly, the term applies to any domain. Quoting from the research update:

By deconfusion, I mean something like “making it so that you can think about a given topic without continuously accidentally spouting nonsense.”

Posts tagged Deconfusion
7
60Looking Deeper at DeconfusionΩ
adamShimi
2y
Ω
13
2
129Exercises in Comprehensive Information Gathering
johnswentworth
3y
16
2
96Deconfusing Direct vs Amortised OptimizationΩ
beren
6mo
Ω
14
2
90Modelling Transformative AI Risks (MTAIR) Project: IntroductionΩ
Davidmanheim, Aryeh Englander
2y
Ω
0
2
71Builder/Breaker for DeconfusionΩ
abramdemski
9mo
Ω
9
2
69Strategy is the Deconfusion of Action
ryan_b
4y
4
2
53On MIRI's new research directions
Rob Bensinger
5y
12
2
36Applications for Deconfusing Goal-DirectednessΩ
adamShimi
2y
Ω
3
2
35Classification of AI alignment research: deconfusion, "good enough" non-superintelligent AI alignment, superintelligent AI alignment
philip_b
3y
25
2
31Musings on general systems alignmentΩ
Alex Flint
2y
Ω
11
2
24Traps of Formalization in DeconfusionΩ
adamShimi
2y
Ω
7
2
23Open problem: how can we quantify player alignment in 2x2 normal-form games?QΩ
TurnTrout, Vanessa Kosoy
2y
QΩ
59
2
16Approaches to gradient hackingΩ
adamShimi
2y
Ω
8
2
15Alex Turner's Research, Comprehensive Information GatheringΩ
adamShimi
2y
Ω
3
2
14Goal-Directedness and Behavior, ReduxΩ
adamShimi
2y
Ω
4
Load More (15/28)
Add Posts