Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
9 posts
Organization Updates
14 posts
Redwood Research
Adversarial Training
AI Robustness
50
What I've been doing instead of writing
benkuhn
1y
3
45
Two clarifications about "Strategic Background"
Rob Bensinger
4y
6
37
Genomic Prediction is now offering embryo selection
gwern
4y
1
35
Get genotyped for free ( If your IQ is high enough)
David Althaus
11y
63
27
What's up with Arbital?
Alexei
5y
91
25
Help the Brain Preservation Foundation
aurellem
9y
20
25
RAISE is looking for full-time content developers
4y
5
24
Giving What We Can needs your help!
RobertWiblin
7y
6
7
Symbiosis - An Intentional Community For Radical Self-Improvement
Matt Goldenberg
4y
0
184
High-stakes alignment via adversarial training [Redwood Research report]
dmz
7mo
29
164
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
LawrenceC
17d
9
159
Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley
maxnadeau
1mo
14
143
Takeaways from our robust injury classifier project [Redwood Research]
dmz
3mo
9
121
Redwood Research’s current project
Buck
1y
29
105
Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
KevinRoWang
1mo
5
98
Why I'm excited about Redwood Research's current project
paulfchristiano
1y
6
50
We're Redwood Research, we do applied alignment research, AMA
Nate Thomas
1y
3
44
Redwood's Technique-Focused Epistemic Strategy
adamShimi
1y
1
31
Latent Adversarial Training
Adam Jermyn
5mo
9
28
Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing
Buck
6mo
0
26
Causal scrubbing: results on a paren balance checker
LawrenceC
17d
0
18
Causal scrubbing: Appendix
LawrenceC
17d
0
15
AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler
DanielFilan
4mo
0