Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
123 posts
Interpretability (ML & AI)
Myopia
Self Fulfilling/Refuting Prophecies
AI Success Models
Lottery Ticket Hypothesis
Conservatism (AI)
Luck
Market making (AI safety technique)
Verification
123 posts
Instrumental Convergence
Corrigibility
Deconfusion
Orthogonality Thesis
Treacherous Turn
Gradient Hacking
Mild Optimization
Quantilization
Satisficer
Gradient Descent
Tripwire
16
An Open Agency Architecture for Safe Transformative AI
davidad
11h
11
140
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme
Collin
5d
18
56
Can we efficiently explain model behaviors?
paulfchristiano
4d
0
250
The Plan - 2022 Update
johnswentworth
19d
33
235
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
151
Re-Examining LayerNorm
Eric Winsor
19d
8
35
Extracting and Evaluating Causal Direction in LLMs' Activations
Fabien Roger
6d
2
21
Paper: Transformers learn in-context by gradient descent
LawrenceC
4d
11
26
[ASoT] Natural abstractions and AlphaZero
Ulisse Mini
10d
1
56
Multi-Component Learning and S-Curves
Adam Jermyn
20d
24
446
A Mechanistic Interpretability Analysis of Grokking
Neel Nanda
4mo
39
78
By Default, GPTs Think In Plain Sight
Fabien Roger
1mo
16
34
Steering Behaviour: Testing for (Non-)Myopia in Language Models
Evan R. Murphy
15d
16
80
Engineering Monosemanticity in Toy Models
Adam Jermyn
1mo
6
6
(Extremely) Naive Gradient Hacking Doesn't Work
ojorgensen
9h
0
59
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
85
Instrumental convergence is what makes general intelligence possible
tailcalled
1mo
11
6
Assessing the Capabilities of ChatGPT through Success Rates
Zachary Robertson
7d
0
26
Dumb and ill-posed question: Is conceptual research like this MIRI paper on the shutdown problem/Corrigibility "real"
joraine
26d
11
39
A caveat to the Orthogonality Thesis
Wuschel Schulz
1mo
10
4
Contrary to List of Lethality's point 22, alignment's door number 2
False Name, Esq.
6d
1
114
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
johnswentworth
4mo
8
26
People care about each other even though they have imperfect motivational pointers?
TurnTrout
1mo
25
34
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
32
Instrumental convergence in single-agent systems
Edouard Harris
2mo
4
91
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
9
Corrigibility Via Thought-Process Deference
Thane Ruthenis
26d
5
25
CHAI, Assistance Games, And Fully-Updated Deference [Scott Alexander]
berglund
2mo
1