Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
28 posts
Machine Learning (ML)
Lottery Ticket Hypothesis
4 posts
OpenAI
35
Reframing inner alignment
davidad
9d
13
97
Survey of NLP Researchers: NLP is contributing to AGI progress; major catastrophe plausible
Sam Bowman
3mo
6
173
A Bird's Eye View of the ML Field [Pragmatic AI Safety #2]
Dan H
7mo
5
45
Paper+Summary: OMNIGROK: GROKKING BEYOND ALGORITHMIC DATA
Marius Hobbhahn
2mo
11
94
Safety Implications of LeCun's path to machine intelligence
Ivan Vendrov
5mo
16
55
A Data limited future
Donald Hobson
4mo
25
47
Steganography in Chain of Thought Reasoning
A Ray
4mo
13
67
The No Free Lunch theorems and their Razor
Adrià Garriga-alonso
7mo
3
17
[MLSN #5]: Prize Compilation
Dan H
2mo
1
24
Train first VS prune first in neural networks.
Donald Hobson
5mo
5
156
Understanding “Deep Double Descent”
evhub
3y
51
54
Unsolved ML Safety Problems
jsteinhardt
1y
2
17
Grouped Loss may disfavor discontinuous capabilities
Adam Jermyn
5mo
2
60
Gradations of Inner Alignment Obstacles
abramdemski
1y
22
21
My thoughts on OpenAI's Alignment plan
Donald Hobson
10d
0
253
Common misconceptions about OpenAI
Jacob_Hilton
3mo
138
169
the scaling “inconsistency”: openAI’s new insight
nostalgebraist
2y
14
52
Multimodal Neurons in Artificial Neural Networks
Kaj_Sotala
1y
2