Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
62 posts
Interviews
Redwood Research
Organization Updates
AXRP
Adversarial Examples
Adversarial Training
AI Robustness
17 posts
Audio
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
105
Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
KevinRoWang
1mo
5
26
Causal scrubbing: results on a paren balance checker
LawrenceC
17d
0
143
Takeaways from our robust injury classifier project [Redwood Research]
dmz
3mo
9
18
Causal scrubbing: Appendix
LawrenceC
17d
0
184
High-stakes alignment via adversarial training [Redwood Research report]
dmz
7mo
29
31
Ethan Perez on the Inverse Scaling Prize, Language Feedback and Red Teaming
Michaël Trazzi
3mo
0
121
Redwood Research’s current project
Buck
1y
29
98
Why I'm excited about Redwood Research's current project
paulfchristiano
1y
6
108
I wanted to interview Eliezer Yudkowsky but he's busy so I simulated him instead
lsusr
1y
33
31
Latent Adversarial Training
Adam Jermyn
5mo
9
36
AXRP Episode 15 - Natural Abstractions with John Wentworth
DanielFilan
7mo
1
28
Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing
Buck
6mo
0
5
Podcast: Tamera Lanham on AI risk, threat models, alignment proposals, externalized reasoning oversight, and working at Anthropic
Akash
2h
0
42
Podcast: Shoshannah Tekofsky on skilling up in AI safety, visiting Berkeley, and developing novel research ideas
Akash
25d
2
156
Announcing the LessWrong Curated Podcast
Ben Pace
6mo
17
26
Me (Steve Byrnes) on the “Brain Inspired” podcast
Steven Byrnes
1mo
1
12
Interview with Matt Freeman
Evenflair
29d
0
37
Shahar Avin On How To Regulate Advanced AI Systems
Michaël Trazzi
2mo
0
43
How and why to turn everything into audio
KatWoods
4mo
18
22
Which LessWrong content would you like recorded into audio/podcast form?
Ruby
3mo
11
165
Curated conversations with brilliant rationalists
spencerg
1y
18
104
Listen to top LessWrong posts with The Nonlinear Library
KatWoods
1y
27
57
New: use The Nonlinear Library to listen to the top LessWrong posts of all time
KatWoods
8mo
9
20
An Audio Introduction to Nick Bostrom
PeterH
3mo
0
35
Steganography and the CycleGAN - alignment failure case study
Jan Czechowski
6mo
0
13
Podcasts on surveys, slower AI, AI arguments, etc
KatjaGrace
3mo
0