Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
106 posts
Careers
Infra-Bayesianism
SERI MATS
Formal Proof
Domain Theory
Distributional Shifts
79 posts
Audio
Interviews
Organization Updates
Redwood Research
AXRP
Adversarial Examples
Adversarial Training
AI Robustness
135
Job Offering: Help Communicate Infrabayesianism
abramdemski
9mo
21
120
Proofs, Implications, and Models
Eliezer Yudkowsky
10y
218
118
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet)
3mo
18
117
Taking the parameters which seem to matter and rotating them until they don't
Garrett Baker
3mo
48
114
Understanding Infra-Bayesianism: A Beginner-Friendly Video Series
Jack Parker
2mo
6
104
Introduction To The Infra-Bayesianism Sequence
Diffractor
2y
64
103
Externalized reasoning oversight: a research direction for language model alignment
tamera
4mo
22
98
Infra-Bayesian physicalism: a formal theory of naturalized induction
Vanessa Kosoy
1y
20
94
Evaluations project @ ARC is hiring a researcher and a webdev/engineer
Beth Barnes
3mo
7
84
[Closed] Hiring a mathematician to work on the learning-theoretic AI alignment agenda
Vanessa Kosoy
8mo
21
76
A "Failure to Evaluate Return-on-Time" Fallacy
lionhearted
12y
110
71
SERI MATS Program - Winter 2022 Cohort
Ryan Kidd
2mo
12
68
Neural Tangent Kernel Distillation
Thomas Larsen
2mo
20
67
Career Scouting: Dentistry
koratkar
1mo
5
153
Curated conversations with brilliant rationalists
spencerg
1y
18
143
Redwood Research’s current project
Buck
1y
29
136
High-stakes alignment via adversarial training [Redwood Research report]
dmz
7mo
29
135
Takeaways from our robust injury classifier project [Redwood Research]
dmz
3mo
9
134
Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley
maxnadeau
1mo
14
131
Announcing the LessWrong Curated Podcast
Ben Pace
6mo
17
130
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
LawrenceC
17d
9
116
[Transcript] Richard Feynman on Why Questions
Grognor
10y
45
112
Why I'm excited about Redwood Research's current project
paulfchristiano
1y
6
110
I wanted to interview Eliezer Yudkowsky but he's busy so I simulated him instead
lsusr
1y
33
86
Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small
KevinRoWang
1mo
5
74
Listen to top LessWrong posts with The Nonlinear Library
KatWoods
1y
27
58
AI Alignment Podcast: An Overview of Technical AI Alignment in 2018 and 2019 with Buck Shlegeris and Rohin Shah
Palus Astra
2y
27
57
What I've been doing instead of writing
benkuhn
1y
3