AI ALIGNMENT FORUMTags
AF

Deconfusion

EditHistorySubscribe
Discussion (0)
Help improve this page (3 flags)
EditHistorySubscribe
Discussion (0)
Help improve this page (3 flags)
Deconfusion
Random Tag
Contributors
2Abram Demski

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
Most Relevant
5
25Looking Deeper at Deconfusion
Adam Shimi
1y
2
1
65The Plan
johnswentworth
5mo
11
1
34Modelling Transformative AI Risks (MTAIR) Project: Introduction
David Manheim, Aryeh Englander
9mo
0
1
24Applications for Deconfusing Goal-Directedness
Adam Shimi
9mo
0
1
21Musings on general systems alignment
Alex Flint
1y
1
1
15Open problem: how can we quantify player alignment in 2x2 normal-form games?Q
Alex Turner, Vanessa Kosoy
1y
Q
21
1
15Traps of Formalization in Deconfusion
Adam Shimi
10mo
1
1
12Alex Turner's Research, Comprehensive Information Gathering
Adam Shimi
1y
3
1
9Approaches to gradient hacking
Adam Shimi
9mo
7
1
8Goal-Directedness and Behavior, Redux
Adam Shimi
9mo
2
1
10Power-seeking for successive choices
Adam Shimi
9mo
9
1
7A review of "Agents and Devices"
Adam Shimi
9mo
0
0
47Clarifying inner alignment terminology
Evan Hubinger
2y
13
Add Posts