Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
11 posts
Redwood Research
Adversarial Training
2 posts
106
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
LawrenceC
17d
9
118
Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley
maxnadeau
1mo
14
134
Takeaways from our robust injury classifier project [Redwood Research]
dmz
3mo
9
73
Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
KevinRoWang
1mo
5
98
High-stakes alignment via adversarial training [Redwood Research report]
dmz
7mo
29
54
Redwood's Technique-Focused Epistemic Strategy
adamShimi
1y
1
18
AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler
DanielFilan
4mo
0
170
Redwood Research’s current project
Buck
1y
29
15
Causal scrubbing: Appendix
LawrenceC
17d
0
27
Causal scrubbing: results on a paren balance checker
LawrenceC
17d
0
129
Why I'm excited about Redwood Research's current project
paulfchristiano
1y
6
18
Latent Adversarial Training
Adam Jermyn
5mo
9
39
Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing
Buck
6mo
0