Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
86 posts
Interpretability (ML & AI)
Lottery Ticket Hypothesis
9 posts
AI Success Models
Conservatism (AI)
Market making (AI safety technique)
Verification
106
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme
Collin
5d
18
70
Can we efficiently explain model behaviors?
paulfchristiano
4d
0
172
The Plan - 2022 Update
johnswentworth
19d
33
31
Paper: Transformers learn in-context by gradient descent
LawrenceC
4d
11
36
[ASoT] Natural abstractions and AlphaZero
Ulisse Mini
10d
1
83
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
58
Multi-Component Learning and S-Curves
Adam Jermyn
20d
24
47
Re-Examining LayerNorm
Eric Winsor
19d
8
64
Engineering Monosemanticity in Toy Models
Adam Jermyn
1mo
6
9
Extracting and Evaluating Causal Direction in LLMs' Activations
Fabien Roger
6d
2
230
A Mechanistic Interpretability Analysis of Grokking
Neel Nanda
4mo
39
42
By Default, GPTs Think In Plain Sight
Fabien Roger
1mo
16
18
Subsets and quotients in interpretability
Erik Jenner
18d
1
51
Real-Time Research Recording: Can a Transformer Re-Derive Positional Info?
Neel Nanda
1mo
14
10
An Open Agency Architecture for Safe Transformative AI
davidad
11h
11
111
Conversation with Eliezer: What do you want the system to do?
Akash
5mo
38
65
Various Alignment Strategies (and how likely they are to work)
Logan Zoellner
7mo
34
81
A positive case for how we might succeed at prosaic AI alignment
evhub
1y
47
20
Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios
Evan R. Murphy
7mo
0
63
Solving the whole AGI control problem, version 0.0001
Steven Byrnes
1y
7
14
If AGI were coming in a year, what should we do?
MichaelStJules
8mo
16
33
Pessimism About Unknown Unknowns Inspires Conservatism
michaelcohen
2y
2
17
RFC: Philosophical Conservatism in AI Alignment Research
Gordon Seidoh Worley
4y
13