Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
16 posts
Scaling Laws
4 posts
GAN
364
chinchilla's wild implications
nostalgebraist
4mo
114
27
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
47
Smoke without fire is scary
Adam Jermyn
2mo
22
15
Updates on scaling laws for foundation models from ' Transcending Scaling Laws with 0.1% Extra Compute'
Nick_Greig
1mo
2
83
Causal confusion as an argument against the scaling hypothesis
RobertKirk
6mo
30
7
Massive Scaling Should be Frowned Upon
harsimony
1mo
6
62
Ethan Caballero on Private Scaling Progress
Michaël Trazzi
7mo
1
43
A Quick Note on AI Scaling Asymptotes
alyssavance
6mo
6
20
Machine Learning Model Sizes and the Parameter Gap [abridged]
Pablo Villalobos
5mo
0
79
Thoughts on the Alignment Implications of Scaling Language Models
leogao
1y
11
51
NVIDIA and Microsoft releases 530B parameter transformer model, Megatron-Turing NLG
Ozyrus
1y
36
49
A closer look at chess scalings (into the past)
hippke
1y
14
23
Compute Trends — Comparison to OpenAI’s AI and Compute
lennart
9mo
3
35
My ML Scaling bibliography
gwern
1y
9
32
Google's new text-to-image model - Parti, a demonstration of scaling benefits
Kayden
6mo
4
18
GAN Discriminators Don't Generalize?
tryactions
2y
7
4
GPT-3 + GAN
stick109
2y
4
0
Generative adversarial models, informed by arguments
jessicata
6y
0