Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
4 posts
AXRP
Adversarial Examples
23 posts
Redwood Research
Organization Updates
Adversarial Training
AI Robustness
35
If I were a well-intentioned AI... I: Image classifier
Stuart_Armstrong
2y
4
31
[AN #62] Are adversarial examples caused by real but imperceptible features?
Rohin Shah
3y
10
16
AXRP Episode 1 - Adversarial Policies with Adam Gleave
DanielFilan
1y
5
18
The Goodhart Game
John_Maxwell
3y
5
96
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
LawrenceC
17d
9
109
Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley
maxnadeau
1mo
14
26
Causal scrubbing: results on a paren balance checker
LawrenceC
17d
0
67
Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
KevinRoWang
1mo
5
127
Takeaways from our robust injury classifier project [Redwood Research]
dmz
3mo
9
14
Causal scrubbing: Appendix
LawrenceC
17d
0
88
High-stakes alignment via adversarial training [Redwood Research report]
dmz
7mo
29
165
Redwood Research’s current project
Buck
1y
29
126
Why I'm excited about Redwood Research's current project
paulfchristiano
1y
6
38
Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing
Buck
6mo
0
17
AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler
DanielFilan
4mo
0
52
Redwood's Technique-Focused Epistemic Strategy
adamShimi
1y
1
62
We're Redwood Research, we do applied alignment research, AMA
Nate Thomas
1y
3
64
What I've been doing instead of writing
benkuhn
1y
3