Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
13 posts
AI Alignment Fieldbuilding
Information Hazards
PIBBSS
Privacy
8 posts
SERI MATS
Distillation & Pedagogy
164
Most People Start With The Same Few Bad Ideas
johnswentworth
3mo
30
149
Lessons learned from talking to >100 academics about AI safety
Marius Hobbhahn
2mo
16
139
The Fusion Power Generator Scenario
johnswentworth
2y
29
82
Principles of Privacy for Alignment Research
johnswentworth
4mo
30
78
ML Alignment Theory Program under Evan Hubinger
Oliver Zhang
1y
3
71
Conjecture: Internal Infohazard Policy
Connor Leahy
4mo
6
70
Needed: AI infohazard policy
Vanessa Kosoy
2y
17
39
[An email with a bunch of links I sent an experienced ML researcher interested in learning about Alignment / x-safety.]
David Scott Krueger (formerly: capybaralet)
3mo
1
37
Economic AI Safety
jsteinhardt
1y
3
20
Reflections on the PIBBSS Fellowship 2022
Nora_Ammann
9d
0
17
Announcing AISIC 2022 - the AI Safety Israel Conference, October 19-20
Davidmanheim
3mo
0
6
AI alignment as “navigating the space of intelligent behaviour”
Nora_Ammann
3mo
0
0
PIBBSS (AI alignment) is hiring for a Project Manager
Nora_Ammann
3mo
0
163
Call For Distillers
johnswentworth
8mo
42
66
SERI MATS Program - Winter 2022 Cohort
Ryan Kidd
2mo
12
30
Behaviour Manifolds and the Hessian of the Total Loss - Notes and Criticism
Spencer Becker-Kahn
3mo
4
27
[Request for Distillation] Coherence of Distributed Decisions With Different Inputs Implies Conditioning
johnswentworth
7mo
14
17
A distillation of Evan Hubinger's training stories (for SERI MATS)
Daphne_W
5mo
1
16
Auditing games for high-level interpretability
Paul Colognese
1mo
1
15
Abram Demski's ELK thoughts and proposal - distillation
Rubi J. Hudson
5mo
4
15
What to include in a guest lecture on existential risks from AI?
Aryeh Englander
8mo
9