Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
10 posts
Threat Models
4 posts
Sharp Left Turn
44
AI X-risk >35% mostly based on a recent peer-reviewed argument
michaelcohen
1mo
31
240
Another (outer) alignment failure story
paulfchristiano
1y
38
53
Rogue AGI Embodies Valuable Intellectual Property
Mark Xu
1y
9
416
What failure looks like
paulfchristiano
3y
49
40
AI Neorealism: a threat model & success criterion for existential safety
davidad
5d
0
69
Survey on AI existential risk scenarios
Sam Clarke
1y
11
111
Less Realistic Tales of Doom
Mark Xu
1y
13
36
Vignettes Workshop (AI Impacts)
Daniel Kokotajlo
1y
3
91
Distinguishing AI takeover scenarios
Sam Clarke
1y
11
28
Investigating AI Takeover Scenarios
Sammy Martin
1y
1
67
We may be able to see sharp left turns coming
Ethan Perez
3mo
26
30
Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Vika
25d
4
292
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
6mo
48
83
Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Vika
4mo
3