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
72
Far-UVC Light Update: No, LEDs are not around the corner (tweetstorm)
Davidmanheim
1mo
27
-26
AI can exploit safety plans posted on the Internet
Peter S. Park
16d
4
26
Intercept article about lab accidents
ChristianKl
1mo
9
0
AI Safety in a Vulnerable World: Requesting Feedback on Preliminary Thoughts
Jordan Arel
14d
2
8
4 Key Assumptions in AI Safety
Prometheus
1mo
5
3
Why do we post our AI safety plans on the Internet?
Peter S. Park
1mo
4
4
Value of Querying 100+ People About Humanity's Future
rodeo_flagellum
1mo
3
13
Double Asteroid Redirection Test succeeds
sanxiyn
2mo
5
44
New US Senate Bill on X-Risk Mitigation [Linkpost]
Evan R. Murphy
5mo
12
23
The Dumbest Possible Gets There First
Artaxerxes
4mo
7
0
The Shape of Things to Come
Alex Beyman
2mo
3
22
Case Rates to Sequencing Reads
jefftk
3mo
4
4
X-risk Mitigation Does Actually Require Longtermism
DragonGod
1mo
1
33
Cultivating Valiance
Shoshannah Tekofsky
4mo
4
10
Characterizing Intrinsic Compositionality in Transformers with Tree Projections
Ulisse Mini
1mo
2
179
Some AI research areas and their relevance to existential safety
Andrew_Critch
2y
40
143
2021 AI Alignment Literature Review and Charity Comparison
Larks
12mo
26
11
The Mind Is Not Designed For Thinking
CronoDAS
13y
7
55
New paper from MIRI: "Toward idealized decision theory"
So8res
8y
22
37
New paper: Corrigibility with Utility Preservation
Koen.Holtman
3y
11
9
[Preprint for commenting] Digital Immortality: Theory and Protocol for Indirect Mind Uploading
avturchin
4y
5
53
Hope Function
gwern
10y
8
36
Some conceptual highlights from “Disjunctive Scenarios of Catastrophic AI Risk”
Kaj_Sotala
4y
4
3
Social Choice Ethics in Artificial Intelligence (paper challenging CEV-like approaches to choosing an AI's values)
Kaj_Sotala
5y
0
72
[link] Why Self-Control Seems (but may not be) Limited
Kaj_Sotala
8y
10
4
A discussion of the paper, "Large Language Models are Zero-Shot Reasoners"
HiroSakuraba
6mo
0
11
IQ Scores Fail to Predict Academic Performance in Children With Autism
InquilineKea
12y
9
29
Study on what makes people approve or condemn mind upload technology; references LW
Kaj_Sotala
4y
0