Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
98 posts
Existential Risk
Biosecurity
39 posts
Academic Papers
70
Far-UVC Light Update: No, LEDs are not around the corner (tweetstorm)
Davidmanheim
1mo
27
190
On saving one's world
Rob Bensinger
7mo
5
224
A Quick Guide to Confronting Doom
Ruby
8mo
36
23
Intercept article about lab accidents
ChristianKl
1mo
9
126
Intergenerational trauma impeding cooperative existential safety efforts
Andrew_Critch
6mo
28
114
Leaving Google, Joining the Nucleic Acid Observatory
jefftk
6mo
4
20
4 Key Assumptions in AI Safety
Prometheus
1mo
5
87
In defense of flailing, with foreword by Bill Burr
lc
6mo
8
50
Anti-squatted AI x-risk domains index
plex
4mo
3
62
Resources I send to AI researchers about AI safety
Vael Gates
6mo
12
3
AI Safety in a Vulnerable World: Requesting Feedback on Preliminary Thoughts
Jordan Arel
14d
2
35
Cultivating Valiance
Shoshannah Tekofsky
4mo
4
35
The Dumbest Possible Gets There First
Artaxerxes
4mo
7
9
Value of Querying 100+ People About Humanity's Future
rodeo_flagellum
1mo
3
164
2021 AI Alignment Literature Review and Charity Comparison
Larks
12mo
26
12
Characterizing Intrinsic Compositionality in Transformers with Tree Projections
Ulisse Mini
1mo
2
199
Some AI research areas and their relevance to existential safety
Andrew_Critch
2y
40
43
Stanford Encyclopedia of Philosophy on AI ethics and superintelligence
Kaj_Sotala
2y
19
7
A discussion of the paper, "Large Language Models are Zero-Shot Reasoners"
HiroSakuraba
6mo
0
42
Human-AI Collaboration
Rohin Shah
3y
7
17
Deep limitations? Examining expert disagreement over deep learning
Richard_Ngo
1y
5
35
New paper: Corrigibility with Utility Preservation
Koen.Holtman
3y
11
23
New paper: The Incentives that Shape Behaviour
RyanCarey
2y
5
84
Tiling Agents for Self-Modifying AI (OPFAI #2)
Eliezer Yudkowsky
9y
259
33
Some conceptual highlights from “Disjunctive Scenarios of Catastrophic AI Risk”
Kaj_Sotala
4y
4
20
Can this model grade a test without knowing the answers?
Elizabeth
3y
3
26
Good News for Immunostimulants
sarahconstantin
4y
9
54
[link] Why Self-Control Seems (but may not be) Limited
Kaj_Sotala
8y
10