J. Carlsmith

Artificial Intelligence · 2022

A researcher in the Science corpus: 1 paper; trusts 6 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 17 citations into it
• Safety, Robustness & Interpretability — 8 citations into it; #1,903 of 2,251 by trust here, #2,180 by citations

Whom J. Carlsmith trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Paul Christiano
2. S. Omohundro
3. Eliezer Yudkowsky
4. Joseph Henrich
5. Anne Lauscher
6. Dario Amodei
7. Jan Leike
8. David Krueger
9. David Silver

Who trusts J. Carlsmith overall

1. Richard Ngo
2. Leo Gao
3. Wes Gurnee
4. Tianhao Shen

Papers from J. Carlsmith's perspective

Ordered by how strongly the researchers J. Carlsmith trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
8. ImageNet: A large-scale hierarchical image database
9. Asynchronous Methods for Deep Reinforcement Learning
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Is Power-Seeking AI an Existential Risk? (2022) — 163 citations