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
265
Lessons learned from talking to >100 academics about AI safety
Marius Hobbhahn
2mo
16
167
Conjecture: Internal Infohazard Policy
Connor Leahy
4mo
6
158
Most People Start With The Same Few Bad Ideas
johnswentworth
3mo
30
133
The Fusion Power Generator Scenario
johnswentworth
2y
29
86
ML Alignment Theory Program under Evan Hubinger
Oliver Zhang
1y
3
54
Principles of Privacy for Alignment Research
johnswentworth
4mo
30
53
[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
52
Needed: AI infohazard policy
Vanessa Kosoy
2y
17
42
Reflections on the PIBBSS Fellowship 2022
Nora_Ammann
9d
0
33
Economic AI Safety
jsteinhardt
1y
3
30
AI alignment as “navigating the space of intelligent behaviour”
Nora_Ammann
3mo
0
18
PIBBSS (AI alignment) is hiring for a Project Manager
Nora_Ammann
3mo
0
9
Announcing AISIC 2022 - the AI Safety Israel Conference, October 19-20
Davidmanheim
3mo
0
221
Call For Distillers
johnswentworth
8mo
42
76
SERI MATS Program - Winter 2022 Cohort
Ryan Kidd
2mo
12
40
Auditing games for high-level interpretability
Paul Colognese
1mo
1
40
Behaviour Manifolds and the Hessian of the Total Loss - Notes and Criticism
Spencer Becker-Kahn
3mo
4
25
What to include in a guest lecture on existential risks from AI?
Aryeh Englander
8mo
9
17
[Request for Distillation] Coherence of Distributed Decisions With Different Inputs Implies Conditioning
johnswentworth
7mo
14
15
Abram Demski's ELK thoughts and proposal - distillation
Rubi J. Hudson
5mo
4
13
A distillation of Evan Hubinger's training stories (for SERI MATS)
Daphne_W
5mo
1