Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
153 posts
Interpretability (ML & AI)
GPT
Machine Learning (ML)
DeepMind
OpenAI
Truth, Semantics, & Meaning
AI Success Models
Bounties & Prizes (active)
AI-assisted Alignment
Lottery Ticket Hypothesis
Computer Science
Honesty
168 posts
Conjecture (org)
Oracle AI
Myopia
Language Models
Refine
Deconfusion
Agency
AI Boxing (Containment)
Deceptive Alignment
Scaling Laws
Deception
Acausal Trade
11
An Open Agency Architecture for Safe Transformative AI
davidad
11h
11
114
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme
Collin
5d
18
223
A challenge for AGI organizations, and a challenge for readers
Rob Bensinger
19d
30
183
The Plan - 2022 Update
johnswentworth
19d
33
48
Predicting GPU performance
Marius Hobbhahn
6d
24
32
Paper: Transformers learn in-context by gradient descent
LawrenceC
4d
11
59
Reframing inner alignment
davidad
9d
13
90
[Link] Why I’m optimistic about OpenAI’s alignment approach
janleike
15d
13
37
[ASoT] Natural abstractions and AlphaZero
Ulisse Mini
10d
1
56
Re-Examining LayerNorm
Eric Winsor
19d
8
61
Multi-Component Learning and S-Curves
Adam Jermyn
20d
24
18
An exploration of GPT-2's embedding weights
Adam Scherlis
7d
2
11
Extracting and Evaluating Causal Direction in LLMs' Activations
Fabien Roger
6d
2
19
My thoughts on OpenAI's Alignment plan
Donald Hobson
10d
0
28
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
27
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
43
Proper scoring rules don’t guarantee predicting fixed points
Johannes_Treutlein
4d
2
64
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
143
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
35
Side-channels: input versus output
davidad
8d
9
96
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
108
What I Learned Running Refine
adamShimi
26d
5
178
Mysteries of mode collapse
janus
1mo
35
41
Steering Behaviour: Testing for (Non-)Myopia in Language Models
Evan R. Murphy
15d
16
145
Decision theory does not imply that we get to have nice things
So8res
2mo
53
85
Trying to Make a Treacherous Mesa-Optimizer
MadHatter
1mo
13
52
Conjecture Second Hiring Round
Connor Leahy
27d
0
31
Searching for Search
NicholasKees
22d
6